Stars
Explainable Video Action Reasoning via Prior Knowledge and State Transitions
Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021
[CVPR'2024 Highlight] Official PyTorch implementation of the paper "VTimeLLM: Empower LLM to Grasp Video Moments".
Code for the ECCV'22 paper "Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos".
A video database bridging human actions and human-object relationships
[NeurIPS2023] Neural-Logic Human-Object Interaction Detection
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
Open-source and strong foundation image recognition models.
Tips for Writing a Research Paper using LaTeX
A simple code for plotting figure, colorbar, and cropping with python
Code implementation for paper titled "HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision"
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。
Fitness Action Quality Assessment or your AI-Fitness Coach [ECCV 2022]
Knowledgebase embedding with your company data
Home Action Genome: Cooperative Contrastive Action Understanding
[IROS 2023] Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition
LAVIS - A One-stop Library for Language-Vision Intelligence
Official repository of paper "Subobject-level Image Tokenization"
🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.
A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
Top free VPN (ClashX & V2Ray proxy) with subscription links. [免费VPN、免费梯子、免费科学上网、免费订阅链接、免费节点、精选、ClashX & V2Ray 教程]