publications

2026

1. AAAI

   FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding

   João Pereira, Vasco Lopes, João Neves, and 1 more author

   In Proceedings of the 40th AAAI Conference on Artificial Intelligence, 2026

   Bib

   @inproceedings{aaai2026,
     title = {{FineVAU}: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding},
     author = {Pereira, João and Lopes, Vasco and Neves, João and Semedo, David},
     booktitle = {Proceedings of the 40th AAAI Conference on Artificial Intelligence},
     year = {2026},
     address = {Singapore},
   }

2. EACL

   VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval

   Diogo Glória-Silva, David Semedo, and João Magalhães

   In Findings of the Association for Computational Linguistics: EACL 2026, 2026

   Bib

   @inproceedings{vigia2026,
     title = {{VIGiA}: Instructional Video Guidance via Dialogue Reasoning and Retrieval},
     author = {Glória-Silva, Diogo and Semedo, David and Magalhães, João},
     booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
     pages = {4003--4030},
     publisher = {Association for Computational Linguistics},
     year = {2026},
     address = {Rabat, Morocco},
     url = {https://aclanthology.org/2026.findings-eacl.208/},
   }

3. PROPOR

   AMALIA: A Fully Open Large Language Model for European Portuguese

   Afonso Simplício, Gonçalo Vinagre, Miguel Moura Ramos, and 19 more authors

   In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026), 2026

   Bib

   @inproceedings{amalia2026,
     title = {{AMALIA}: A Fully Open Large Language Model for {European} {Portuguese}},
     author = {Simplício, Afonso and Vinagre, Gonçalo and Ramos, Miguel Moura and Tavares, Diogo and Ferreira, Rafael and Attanasio, Giuseppe and Alves, Duarte M. and Calvo, Inês and Vieira, Inês and Guerra, Rui and Furtado, James and Canaverde, Beatriz and Paulo, Iago and Ramos, Vasco and Glória-Silva, Diogo and Faria, Miguel and Treviso, Marcos and Gomes, Daniel and Gomes, Pedro and Semedo, David and Martins, André and Magalhães, João},
     booktitle = {Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026)},
     pages = {380--391},
     publisher = {Association for Computational Linguistics},
     year = {2026},
     address = {Salvador, Brazil},
     url = {https://aclanthology.org/2026.propor-1.38/},
   }

4. PROPOR

   ALBA: A European Portuguese Benchmark for Evaluating Language and Linguistic Dimensions in Generative LLMs

   Inês Vieira, Inês Calvo, Iago Paulo, and 6 more authors

   In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026), 2026

   Bib

   @inproceedings{alba2026,
     title = {{ALBA}: A {European} {Portuguese} Benchmark for Evaluating Language and Linguistic Dimensions in Generative {LLMs}},
     author = {Vieira, Inês and Calvo, Inês and Paulo, Iago and Furtado, James and Ferreira, Rafael and Tavares, Diogo and Glória-Silva, Diogo and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026)},
     pages = {697--707},
     publisher = {Association for Computational Linguistics},
     year = {2026},
     address = {Salvador, Brazil},
     url = {https://aclanthology.org/2026.propor-1.69/},
   }

5. LREC

   PHEB: An European Portuguese High School-Level LLM Benchmark

   Diogo Tavares, Rafael Ferreira, Afonso Simplício, and 6 more authors

   In Proceedings of LREC-COLING 2026, 2026

   Bib

   @inproceedings{pheb2026,
     title = {{PHEB}: An European Portuguese High School-Level {LLM} Benchmark},
     author = {Tavares, Diogo and Ferreira, Rafael and Simplício, Afonso and Vinagre, Gonçalo and Condez, Ana Carolina and Calvo, Inês and Vieira, Inês and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of LREC-COLING 2026},
     publisher = {ELRA and ICCL},
     year = {2026},
   }

2025

1. EMNLP

   Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations

   Diogo Tavares, David Semedo, Alexander Rudnicky, and 1 more author

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

   Abs DOI Bib

   Large Language Models (LLMs) are increasingly costly to fine-tune due to their size, with embedding layers alone accounting for up to 20% of model parameters. We introduce TinyTE, a novel PEFT approach that steers model behavior via minimal translational transformations in the embedding space. TinyTE modifies input embeddings without altering hidden layers, achieving competitive performance while requiring approximately 0.0001% of the parameters needed for full fine-tuning.

   @inproceedings{tinyte,
     title = {Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations},
     author = {Tavares, Diogo and Semedo, David and Rudnicky, Alexander and Magalhães, João},
     booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
     pages = {22960--22978},
     publisher = {Association for Computational Linguistics},
     year = {2025},
     address = {Suzhou, China},
     url = {https://aclanthology.org/2025.emnlp-main.1170/},
     doi = {10.18653/v1/2025.emnlp-main.1170},
   }

2. ICME

   Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding

   João Pereira, Vasco Lopes, David Semedo, and 1 more author

   In IEEE International Conference on Multimedia and Expo (ICME 2025), 2025

   DOI Bib

   @inproceedings{icme2025,
     title = {Self-{ReS}: Self-Reflection in Large Vision-Language Models for Long Video Understanding},
     author = {Pereira, João and Lopes, Vasco and Semedo, David and Neves, João},
     booktitle = {IEEE International Conference on Multimedia and Expo (ICME 2025)},
     pages = {1--9},
     publisher = {IEEE},
     year = {2025},
     address = {Nantes, France},
     url = {https://doi.org/10.1109/ICME59968.2025.11209055},
     doi = {10.1109/ICME59968.2025.11209055},
   }

3. EPIA

   Unveiling MicroRNA Biomarkers for Breast Cancer Sub-typing Using Discriminative Models

   João Mota, José Romano, Ana Rita Grosso, and 3 more authors

   In Progress in Artificial Intelligence — 24th EPIA Conference on Artificial Intelligence (EPIA 2025), 2025

   DOI Bib

   @inproceedings{epia2025,
     title = {Unveiling {MicroRNA} Biomarkers for Breast Cancer Sub-typing Using Discriminative Models},
     author = {Mota, João and Romano, José and Grosso, Ana Rita and Conde, João and Mendes, Bárbara and Semedo, David},
     booktitle = {Progress in Artificial Intelligence — 24th EPIA Conference on Artificial Intelligence (EPIA 2025)},
     series = {Lecture Notes in Computer Science},
     volume = {16121},
     pages = {68--80},
     publisher = {Springer},
     year = {2025},
     address = {Faro, Portugal},
     url = {https://doi.org/10.1007/978-3-032-05176-9_6},
     doi = {10.1007/978-3-032-05176-9_6},
   }

4. IbPRIA

   Towards Event-Driven Evaluation of Surveillance Video Understanding Using Natural Language

   João Pereira, Vasco Lopes, João Neves, and 1 more author

   In Pattern Recognition and Image Analysis — 12th Iberian Conference (IbPRIA 2025), 2025

   DOI Bib

   @inproceedings{ibpria2025,
     title = {Towards Event-Driven Evaluation of Surveillance Video Understanding Using Natural Language},
     author = {Pereira, João and Lopes, Vasco and Neves, João and Semedo, David},
     booktitle = {Pattern Recognition and Image Analysis — 12th Iberian Conference (IbPRIA 2025)},
     series = {Lecture Notes in Computer Science},
     volume = {15938},
     pages = {43--55},
     publisher = {Springer},
     year = {2025},
     address = {Coimbra, Portugal},
     url = {https://doi.org/10.1007/978-3-031-99568-2_4},
     doi = {10.1007/978-3-031-99568-2_4},
   }

5. RECPAD

   Chain-of-Anomaly Thoughts with Large Vision-Language Models

   Pedro Domingos, João Pereira, Vasco Lopes, and 2 more authors

   In Proceedings of the 31st Portuguese Conference on Pattern Recognition (RECPAD 2025), 2025

   Bib

   @inproceedings{recpad2025,
     title = {Chain-of-Anomaly Thoughts with Large Vision-Language Models},
     author = {Domingos, Pedro and Pereira, João and Lopes, Vasco and Neves, João and Semedo, David},
     booktitle = {Proceedings of the 31st Portuguese Conference on Pattern Recognition (RECPAD 2025)},
     year = {2025},
   }

6. arXiv

   RedTWIZ: Diverse LLM Red Teaming via Adaptive Attack Planning

   Artur Horal, Daniel Pina, Henrique Paz, and 7 more authors

   2025

   Bib

   @techreport{redtwiz,
     title = {{RedTWIZ}: Diverse {LLM} Red Teaming via Adaptive Attack Planning},
     author = {Horal, Artur and Pina, Daniel and Paz, Henrique and Paulo, Iago and Soares, João and Ferreira, Rafael and Tavares, Diogo and Glória-Silva, Diogo and Magalhães, João and Semedo, David},
     institution = {Amazon Science},
     year = {2025},
     url = {https://doi.org/10.48550/arXiv.2510.06994},
   }

2024

1. EMNLP

   Show and Guide: Instructional-Plan Grounded Vision and Language Model

   Diogo Glória-Silva, David Semedo, and João Magalhães

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

   DOI Bib

   @inproceedings{emnlp2024_showguide,
     title = {Show and Guide: Instructional-Plan Grounded Vision and Language Model},
     author = {Glória-Silva, Diogo and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
     pages = {21371--21389},
     publisher = {Association for Computational Linguistics},
     year = {2024},
     address = {Miami, FL, USA},
     url = {https://doi.org/10.18653/v1/2024.emnlp-main.1191},
     doi = {10.18653/v1/2024.emnlp-main.1191},
   }

2. EMNLP

   Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants

   Rafael Ferreira, David Semedo, and João Magalhães

   In Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

   DOI Bib

   @inproceedings{emnlp2024_multitrait,
     title = {Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants},
     author = {Ferreira, Rafael and Semedo, David and Magalhães, João},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
     pages = {16105--16130},
     publisher = {Association for Computational Linguistics},
     year = {2024},
     address = {Miami, FL, USA},
     url = {https://doi.org/10.18653/v1/2024.findings-emnlp.945},
     doi = {10.18653/v1/2024.findings-emnlp.945},
   }

3. EMNLP

   V-GlórIA — Customizing Large Vision and Language Models to European Portuguese

   Afonso Simplício, David Semedo, and João Magalhães

   In Proceedings of the 1st Workshop on Customizable NLP (CustomNLP4U), EMNLP 2024, 2024

   Workshop at EMNLP 2024 (CORE A*)

   DOI Bib

   @inproceedings{vgloria2024,
     title = {{V-Gl{\'o}rIA} — Customizing Large Vision and Language Models to {European} {Portuguese}},
     author = {Simplício, Afonso and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 1st Workshop on Customizable NLP (CustomNLP4U), EMNLP 2024},
     pages = {317--326},
     publisher = {Association for Computational Linguistics},
     year = {2024},
     address = {Miami, FL, USA},
     url = {https://aclanthology.org/2024.customnlp4u-1.24/},
     doi = {10.18653/v1/2024.customnlp4u-1.24},
     note = {Workshop at EMNLP 2024 (CORE A*)},
   }

4. EACL

   Plan-Grounded Large Language Models for Dual Goal Conversational Settings

   Diogo Glória-Silva, Rafael Ferreira, Diogo Tavares, and 2 more authors

   In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024), 2024

   Bib

   @inproceedings{plan_llm,
     title = {Plan-Grounded Large Language Models for Dual Goal Conversational Settings},
     author = {Glória-Silva, Diogo and Ferreira, Rafael and Tavares, Diogo and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024)},
     pages = {1271--1292},
     publisher = {Association for Computational Linguistics},
     year = {2024},
     address = {St. Julian's, Malta},
     url = {https://aclanthology.org/2024.eacl-long.77},
   }

5. PROPOR

   GlórIA: A Generative and Open Large Language Model for Portuguese

   Ricardo Lopes, João Magalhães, and David Semedo

   In Proceedings of the 16th International Conference on Computational Processing of Portuguese (PROPOR 2024), 2024

   Bib

   @inproceedings{gloria,
     title = {{Gl{\'o}rIA}: A Generative and Open Large Language Model for {Portuguese}},
     author = {Lopes, Ricardo and Magalhães, João and Semedo, David},
     booktitle = {Proceedings of the 16th International Conference on Computational Processing of Portuguese (PROPOR 2024)},
     pages = {441--453},
     publisher = {Association for Computational Linguistics},
     year = {2024},
     address = {Santiago de Compostela, Spain},
     url = {https://aclanthology.org/2024.propor-1.45},
   }

2023

1. SIGIR

   Rating Prediction in Conversational Task Assistants with Behavioral and Conversational Flow Features

   Rafael Ferreira, David Semedo, and João Magalhães

   In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023

   DOI Bib

   @inproceedings{rating_prediction,
     title = {Rating Prediction in Conversational Task Assistants with Behavioral and Conversational Flow Features},
     author = {Ferreira, Rafael and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval},
     pages = {2314--2318},
     publisher = {ACM},
     year = {2023},
     address = {Taipei, Taiwan},
     url = {https://doi.org/10.1145/3539618.3592048},
     doi = {10.1145/3539618.3592048},
   }

2. SIGIR

   Learning to Ask Questions for Zero-Shot Dialogue State Tracking

   Diogo Tavares, David Semedo, Alexander Rudnicky, and 1 more author

   In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023

   DOI Bib

   @inproceedings{sigir2023_dst,
     title = {Learning to Ask Questions for Zero-Shot Dialogue State Tracking},
     author = {Tavares, Diogo and Semedo, David and Rudnicky, Alexander and Magalhães, João},
     booktitle = {Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval},
     pages = {2118--2122},
     publisher = {ACM},
     year = {2023},
     address = {Taipei, Taiwan},
     url = {https://doi.org/10.1145/3539618.3592010},
     doi = {10.1145/3539618.3592010},
   }

3. SIGDIAL

   Grounded Complex Task Segmentation for Conversational Assistants

   Rafael Ferreira, David Semedo, and João Magalhães

   In Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2023), 2023

   DOI Bib

   @inproceedings{segmentation,
     title = {Grounded Complex Task Segmentation for Conversational Assistants},
     author = {Ferreira, Rafael and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2023)},
     pages = {43--54},
     publisher = {Association for Computational Linguistics},
     year = {2023},
     address = {Prague, Czechia},
     url = {https://doi.org/10.18653/v1/2023.sigdial-1.4},
     doi = {10.18653/v1/2023.sigdial-1.4},
   }

4. SIGDIAL

   The Wizard of Curiosities: Enriching Dialogues with Fun Facts

   Frederico Vicente, Rafael Ferreira, David Semedo, and 1 more author

   In Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2023), 2023

   DOI Bib

   @inproceedings{curiosities,
     title = {The Wizard of Curiosities: Enriching Dialogues with Fun Facts},
     author = {Vicente, Frederico and Ferreira, Rafael and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2023)},
     pages = {149--155},
     publisher = {Association for Computational Linguistics},
     year = {2023},
     address = {Prague, Czechia},
     url = {https://doi.org/10.18653/v1/2023.sigdial-1.13},
     doi = {10.18653/v1/2023.sigdial-1.13},
   }

5. EPIA

   Task Conditioned BERT for Joint Intent Detection and Slot-Filling

   Diogo Tavares, Pedro Azevedo, David Semedo, and 2 more authors

   In Progress in Artificial Intelligence — 22nd EPIA Conference on Artificial Intelligence (EPIA 2023), 2023

   DOI Bib

   @inproceedings{epia2023_bert,
     title = {Task Conditioned {BERT} for Joint Intent Detection and Slot-Filling},
     author = {Tavares, Diogo and Azevedo, Pedro and Semedo, David and Sousa, Ricardo Gamelas and Magalhães, João},
     booktitle = {Progress in Artificial Intelligence — 22nd EPIA Conference on Artificial Intelligence (EPIA 2023)},
     series = {Lecture Notes in Computer Science},
     pages = {467--480},
     publisher = {Springer},
     year = {2023},
     address = {Faial Island, Azores},
     url = {https://doi.org/10.1007/978-3-031-49008-8_37},
     doi = {10.1007/978-3-031-49008-8_37},
   }

6. Alexa Prize

   TWIZ-v2: The Wizard of Multimodal Conversational-Stimulus

   Rafael Ferreira, Diogo Tavares, Diogo Silva, and 6 more authors

   In Alexa Prize TaskBot Challenge 2 Proceedings, 2023

   Bib

   @inproceedings{twiz_alexaprize2023,
     title = {{TWIZ-v2}: The Wizard of Multimodal Conversational-Stimulus},
     author = {Ferreira, Rafael and Tavares, Diogo and Silva, Diogo and Valério, Rodrigo and Bordalo, João and Simões, Inês and Ramos, Vasco and Semedo, David and Magalhães, João},
     booktitle = {Alexa Prize TaskBot Challenge 2 Proceedings},
     year = {2023},
     url = {https://www.amazon.science/alexa-prize/proceedings/twiz-the-wizard-of-multimodal-conversational-stimulus},
   }

2022

1. ACM MM

   Understanding News Text and Images Connection with Context-enriched Multimodal Transformers

   Cláudio Bartolomeu, Rui Nóbrega, and David Semedo

   In Proceedings of the 30th ACM International Conference on Multimedia (MM ’22), 2022

   DOI Bib

   @inproceedings{news_images,
     title = {Understanding News Text and Images Connection with Context-enriched Multimodal Transformers},
     author = {Bartolomeu, Cláudio and Nóbrega, Rui and Semedo, David},
     booktitle = {Proceedings of the 30th ACM International Conference on Multimedia (MM '22)},
     pages = {5821--5832},
     publisher = {ACM},
     year = {2022},
     address = {Lisboa, Portugal},
     url = {https://doi.org/10.1145/3503161.3548430},
     doi = {10.1145/3503161.3548430},
   }

2. ACM MM

   TWIZ: The Multimodal Conversational Task Wizard

   Rafael Ferreira, Diogo Silva, Diogo Tavares, and 8 more authors

   In Proceedings of the 30th ACM International Conference on Multimedia (MM ’22), 2022

   Demo paper. Amazon Alexa Prize TaskBot Challenge — Runner-Up 2022, 1st Place 2023

   DOI Bib

   @inproceedings{twiz_mm2022,
     title = {{TWIZ}: The Multimodal Conversational Task Wizard},
     author = {Ferreira, Rafael and Silva, Diogo and Tavares, Diogo and Vicente, Frederico and Bonito, Mariana and Gonçalves, Gustavo and Margarido, Rui and Figueiredo, Paula and Rodrigues, Helder and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 30th ACM International Conference on Multimedia (MM '22)},
     pages = {6997--6999},
     publisher = {ACM},
     year = {2022},
     address = {Lisboa, Portugal},
     url = {https://doi.org/10.1145/3503161.3547741},
     doi = {10.1145/3503161.3547741},
     note = {Demo paper. Amazon Alexa Prize TaskBot Challenge — Runner-Up 2022, 1st Place 2023},
   }

3. ACM MM

   A Conversational Shopping Assistant for Online Virtual Stores

   Tiago Fornelos, Pedro Valente, Rafael Ferreira, and 5 more authors

   In Proceedings of the 30th ACM International Conference on Multimedia (MM ’22), 2022

   Demo paper

   DOI Bib

   @inproceedings{shopping2022,
     title = {A Conversational Shopping Assistant for Online Virtual Stores},
     author = {Fornelos, Tiago and Valente, Pedro and Ferreira, Rafael and Tavares, Diogo and Silva, Diogo and Semedo, David and Magalhães, João and Correia, Nuno},
     booktitle = {Proceedings of the 30th ACM International Conference on Multimedia (MM '22)},
     pages = {6994--6996},
     publisher = {ACM},
     year = {2022},
     address = {Lisboa, Portugal},
     url = {https://doi.org/10.1145/3503161.3547738},
     doi = {10.1145/3503161.3547738},
     note = {Demo paper},
   }

4. ACL

   Polite Task-oriented Dialog Agents: To Generate or to Rewrite?

   Diogo Silva, David Semedo, and João Magalhães

   In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA@ACL 2022), 2022

   Workshop at ACL 2022 (CORE A*)

   DOI Bib

   @inproceedings{wassa_politeness,
     title = {Polite Task-oriented Dialog Agents: To Generate or to Rewrite?},
     author = {Silva, Diogo and Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment \& Social Media Analysis (WASSA@ACL 2022)},
     pages = {304--314},
     publisher = {Association for Computational Linguistics},
     year = {2022},
     address = {Dublin, Ireland},
     url = {https://doi.org/10.18653/v1/2022.wassa-1.34},
     doi = {10.18653/v1/2022.wassa-1.34},
     note = {Workshop at ACL 2022 (CORE A*)},
   }

5. IRJ

   Open-domain conversational search assistants: the Transformer is all you need

   Rafael Ferreira, Mariana Leite, David Semedo, and 1 more author

   Information Retrieval Journal, 2022

   DOI Bib

   @article{irj2022,
     title = {Open-domain conversational search assistants: the {Transformer} is all you need},
     author = {Ferreira, Rafael and Leite, Mariana and Semedo, David and Magalhães, João},
     journal = {Information Retrieval Journal},
     volume = {25},
     number = {2},
     pages = {123--148},
     year = {2022},
     url = {https://doi.org/10.1007/s10791-022-09403-0},
     doi = {10.1007/s10791-022-09403-0},
   }

6. MMSys

   NewsImages: Addressing the Depiction Gap with an Online News Dataset for Text-Image Rematching

   Andreas Lommatzsch, Benjamin Kille, Özlem Özgöbek, and 7 more authors

   In Proceedings of the 13th ACM Multimedia Systems Conference (MMSys ’22), 2022

   DOI Bib

   @inproceedings{newsimages2022,
     title = {{NewsImages}: Addressing the Depiction Gap with an Online News Dataset for Text-Image Rematching},
     author = {Lommatzsch, Andreas and Kille, Benjamin and Özgöbek, Özlem and Zhou, Yuxiao and Tesic, Jelena and Bartolomeu, Cláudio and Semedo, David and Pivovarova, Lidia and Liang, Mingliang and Larson, Martha A.},
     booktitle = {Proceedings of the 13th ACM Multimedia Systems Conference (MMSys '22)},
     pages = {227--233},
     publisher = {ACM},
     year = {2022},
     address = {Athlone, Ireland},
     url = {https://doi.org/10.1145/3524273.3532891},
     doi = {10.1145/3524273.3532891},
   }

7. IbPRIA

   Temporal Convolutional Networks for Robust Face Liveness Detection

   Ruslan Padnevych, David Carmo, David Semedo, and 1 more author

   In Pattern Recognition and Image Analysis — 10th Iberian Conference (IbPRIA 2022), 2022

   DOI Bib

   @inproceedings{ibpria2022,
     title = {Temporal Convolutional Networks for Robust Face Liveness Detection},
     author = {Padnevych, Ruslan and Carmo, David and Semedo, David and Magalhães, João},
     booktitle = {Pattern Recognition and Image Analysis — 10th Iberian Conference (IbPRIA 2022)},
     series = {Lecture Notes in Computer Science},
     pages = {255--267},
     publisher = {Springer},
     year = {2022},
     address = {Aveiro, Portugal},
     url = {https://doi.org/10.1007/978-3-031-04881-4_21},
     doi = {10.1007/978-3-031-04881-4_21},
   }

8. EUSIPCO

   Improving Face Liveness Detection Robustness with Deep Convolutional Generative Adversarial Networks

   Ruslan Padnevych, David Semedo, David Carmo, and 1 more author

   In 30th European Signal Processing Conference (EUSIPCO 2022), 2022

   Bib

   @inproceedings{eusipco_liveness,
     title = {Improving Face Liveness Detection Robustness with Deep Convolutional Generative Adversarial Networks},
     author = {Padnevych, Ruslan and Semedo, David and Carmo, David and Magalhães, João},
     booktitle = {30th European Signal Processing Conference (EUSIPCO 2022)},
     pages = {1866--1870},
     publisher = {IEEE},
     year = {2022},
     address = {Belgrade, Serbia},
     url = {https://ieeexplore.ieee.org/document/9909693},
   }

9. Alexa Prize

   TWIZ: A Conversational Task Wizard with Multimodal Curiosity-Exploration

   Rafael Ferreira, Diogo Silva, Diogo Tavares, and 8 more authors

   In Alexa Prize TaskBot Challenge Proceedings, 2022

   Bib

   @inproceedings{twiz_alexaprize2022,
     title = {{TWIZ}: A Conversational Task Wizard with Multimodal Curiosity-Exploration},
     author = {Ferreira, Rafael and Silva, Diogo and Tavares, Diogo and Vicente, Frederico and Bonito, Mariana and Gonçalves, Gustavo and Margarido, Rui and Figueiredo, Paula and Rodrigues, Helder and Semedo, David and Magalhães, João},
     booktitle = {Alexa Prize TaskBot Challenge Proceedings},
     year = {2022},
     url = {https://assets.amazon.science/4e/15/8910b0f242c5a24c97362fa32d4d/twiz-a-conversational-task-wizard-with-multimodal-curiosity-exploration.pdf},
   }

2021

1. ACM MM

   Assisting News Media Editors with Cohesive Visual Storylines

   Gonçalo Marcelino, David Semedo, André Mourão, and 3 more authors

   In Proceedings of the 29th ACM International Conference on Multimedia (MM ’21), 2021

   Bib

   @inproceedings{assisting_editors,
     title = {Assisting News Media Editors with Cohesive Visual Storylines},
     author = {Marcelino, Gonçalo and Semedo, David and Mourão, André and Blasi, Saverio and Mrak, Marta and Magalhães, João},
     booktitle = {Proceedings of the 29th ACM International Conference on Multimedia (MM '21)},
     publisher = {ACM},
     year = {2021},
     address = {Chengdu, China},
   }

2. ECIR

   Open-Domain Conversational Search Assistant with Transformers

   Rafael Ferreira, Mariana Leite, David Semedo, and 1 more author

   In European Conference on Information Retrieval (ECIR 2021), 2021

   Bib

   @inproceedings{ecir2021_transformers,
     title = {Open-Domain Conversational Search Assistant with Transformers},
     author = {Ferreira, Rafael and Leite, Mariana and Semedo, David and Magalhães, João},
     booktitle = {European Conference on Information Retrieval (ECIR 2021)},
     publisher = {Springer},
     year = {2021},
     address = {Lucca, Italy},
   }

2020

1. ACM MM

   Adaptive Temporal Triplet-Loss for Cross-Modal Embedding Learning

   David Semedo and João Magalhães

   In Proceedings of the 28th ACM International Conference on Multimedia (MM ’20), 2020

   Abs DOI Bib

   We propose a new formulation of the triplet loss function where the traditional static margin is superseded by a novel temporally adaptive maximum margin function, enabling cross-modal embeddings to capture fine-grained temporal correlations across modalities.

   @inproceedings{triplet_loss,
     title = {Adaptive Temporal Triplet-Loss for Cross-Modal Embedding Learning},
     author = {Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 28th ACM International Conference on Multimedia (MM '20)},
     pages = {1152--1161},
     publisher = {ACM},
     year = {2020},
     address = {Seattle, WA, USA},
     url = {https://doi.org/10.1145/3394171.3413540},
     doi = {10.1145/3394171.3413540},
   }

2019

1. ACM MM

   Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints

   David Semedo and João Magalhães

   In Proceedings of the 27th ACM International Conference on Multimedia (MM ’19), 2019

   DOI Bib

   @inproceedings{cross_modal_subspace,
     title = {Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints},
     author = {Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 27th ACM International Conference on Multimedia (MM '19)},
     pages = {75--83},
     publisher = {ACM},
     year = {2019},
     address = {Nice, France},
     url = {https://doi.org/10.1145/3343031.3351030},
     doi = {10.1145/3343031.3351030},
   }

2. ACM MM

   Diachronic Cross-Modal Embeddings

   David Semedo and João Magalhães

   In Proceedings of the 27th ACM International Conference on Multimedia (MM ’19), 2019

   DOI Bib

   @inproceedings{diachronic,
     title = {Diachronic Cross-Modal Embeddings},
     author = {Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 27th ACM International Conference on Multimedia (MM '19)},
     pages = {2061--2069},
     publisher = {ACM},
     year = {2019},
     address = {Nice, France},
     url = {https://doi.org/10.1145/3343031.3351036},
     doi = {10.1145/3343031.3351036},
   }

3. ECIR

   Dynamic-Keyword Extraction from Social Media

   David Semedo and João Magalhães

   In European Conference on Information Retrieval (ECIR 2019), 2019

   Bib

   @inproceedings{ecir2019,
     title = {Dynamic-Keyword Extraction from Social Media},
     author = {Semedo, David and Magalhães, João},
     booktitle = {European Conference on Information Retrieval (ECIR 2019)},
     pages = {852--860},
     publisher = {Springer},
     year = {2019},
     address = {Cologne, Germany},
   }

2018

1. ACM MM

   Temporal Cross-Media Retrieval with Soft-Smoothing

   David Semedo and João Magalhães

   In Proceedings of the 26th ACM International Conference on Multimedia (MM ’18), 2018

   DOI Bib

   @inproceedings{temporal_retrieval,
     title = {Temporal Cross-Media Retrieval with Soft-Smoothing},
     author = {Semedo, David and Magalhães, João},
     booktitle = {Proceedings of the 26th ACM International Conference on Multimedia (MM '18)},
     pages = {1038--1046},
     publisher = {ACM},
     year = {2018},
     address = {Seoul, Republic of Korea},
     url = {https://doi.org/10.1145/3240508.3240665},
     doi = {10.1145/3240508.3240665},
   }