Search Results for author: Brian Mak

Found 10 papers, 3 papers with code

Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition

1 code implementation ECCV 2020 Zhe Niu, Brian Mak

In this paper, we propose novel stochastic modeling of various components of a continuous sign language recognition (CSLR) system that is based on the transformer encoder and connectionist temporal classification (CTC).

Sign Language Recognition

Natural Language-Assisted Sign Language Recognition

1 code implementation CVPR 2023 Ronglai Zuo, Fangyun Wei, Brian Mak

Sign languages are visual languages which convey information by signers' handshape, facial expression, body movement, and so forth.

Sign Language Recognition

On the Audio-visual Synchronization for Lip-to-Speech Synthesis

no code implementations ICCV 2023 Zhe Niu, Brian Mak

Most lip-to-speech (LTS) synthesis models are trained and evaluated under the assumption that the audio-video pairs in the dataset are perfectly synchronized.

Audio-Visual Synchronization Lip to Speech Synthesis +1

Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal

no code implementations26 Dec 2022 Ronglai Zuo, Brian Mak

We name the CSLR model trained with the above auxiliary tasks as consistency-enhanced CSLR, which performs well on signer-dependent datasets in which all signers appear during both training and testing.

Disentanglement Sentence Embedding +2

Two-Stream Network for Sign Language Recognition and Translation

1 code implementation2 Nov 2022 Yutong Chen, Ronglai Zuo, Fangyun Wei, Yu Wu, Shujie Liu, Brian Mak

RGB videos, however, are raw signals with substantial visual redundancy, leading the encoder to overlook the key information for sign language understanding.

Sign Language Recognition Sign Language Translation +2

C2SLR: Consistency-Enhanced Continuous Sign Language Recognition

no code implementations CVPR 2022 Ronglai Zuo, Brian Mak

The backbone of most deep-learning-based continuous sign language recognition (CSLR) models consists of a visual module, a sequential module, and an alignment module.

Sentence Embedding Sentence-Embedding +1

Transformer based Multilingual document Embedding model

no code implementations19 Aug 2020 Wei Li, Brian Mak

One of the current state-of-the-art multilingual document embedding model LASER is based on the bidirectional LSTM neural machine translation model.

Document Embedding Machine Translation +2

NMT-based Cross-lingual Document Embeddings

no code implementations29 Jul 2018 Wei Li, Brian Mak

This paper further adds a distance constraint to the training objective function of NV so that the two embeddings of a parallel document are required to be as close as possible.

Cross-Lingual Document Classification Document Classification +6

Derivation of Document Vectors from Adaptation of LSTM Language Model

no code implementations EACL 2017 Wei Li, Brian Mak

In many natural language processing (NLP) tasks, a document is commonly modeled as a bag of words using the term frequency-inverse document frequency (TF-IDF) vector.

General Classification Genre classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.