Papers by Brian Mak

3 papers
A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News (2024.lrec-main)

Copied to clipboard

Challenge: a new dataset is being developed to enrich resources for sign language research . the dataset is 16.07 hours of sign videos of two signers with a vocabulary of 6,515 glosses and 2,850 Chinese characters or 18K Chinese words.
Approach: They introduce a new Hong Kong sign language dataset called TVB-HKSL-News . the dataset is collected from a TV news program and contains sign videos . they aim to support research in sign language recognition and translation .
Outcome: The proposed dataset supports sign language recognition and translation research in Hong Kong . it consists of 16.07 hours of sign videos of two signers with a vocabulary of 6,515 glosses and 2,850 Chinese characters or 18K Chinese words .
End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation (2025.findings-emnlp)

Copied to clipboard

Challenge: MM-RAG is a promising approach for enhancing the reliability and factuality of large vision-language models . current methods focus on component-level optimizations and necessitate extensive component-specific training datasets .
Approach: They propose a new paradigm that backpropagates global rewards to each component . this backpropage transforms local losses into specific local losses .
Outcome: The proposed paradigm achieves high training efficiency on knowledge-intensive multimodal benchmarks.
Towards Online Continuous Sign Language Recognition and Translation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies on continuous sign language recognition (CSLR) use offline models with high latency and memory usage.
Approach: They develop a sign dictionary and train an isolated sign language recognition model on the dictionary.
Outcome: The proposed model achieves state-of-the-art on three popular benchmarks across task settings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations