Vincent-ZHQ

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

CA-MSER

Code for Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information

Debug_Record

A record for code debugging.

DMER

A survey of deep multimodal emotion recognition.

Landmark-Annotation

关键点标注工具 | Landmark-Annotation

MRDF

Code for Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection

ReMS

Code for Relevance-based Modality Specific Weighting for Multimodal Emotion Recognition

SparseNeRF

[ICCV 2023] SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis

UniS-MMC

Code for UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning (ACL 2023)

Vincent-ZHQ

Vincent-ZHQ/CA-MSER

Code for Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information

Vincent-ZHQ/DMER

A survey of deep multimodal emotion recognition.

Vincent-ZHQ/UniS-MMC

Code for UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning (ACL 2023)

Vincent-ZHQ/MRDF

Code for Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection

Vincent-ZHQ/Debug_Record

A record for code debugging.

Vincent-ZHQ/Landmark-Annotation

关键点标注工具 | Landmark-Annotation

Vincent-ZHQ/ReMS

Code for Relevance-based Modality Specific Weighting for Multimodal Emotion Recognition

Vincent-ZHQ/SparseNeRF

[ICCV 2023] SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis

Vincent-ZHQ/Vincent-ZHQ