https://github.com/madhawav/MML
공식 코드Video Moment Localization using Object Evidence and Reverse Captioning
Papers with Code 아카이브
Video Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 0
- 보존된 평가 기록
- 0
A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/magic-research/PLLaVA
공식 코드PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
https://github.com/marinero4972/cyberv
공식 코드CyberV: Cybernetics for Test-time Scaling in Video Understanding
https://github.com/mayhugotong/videoinsta
공식 코드VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
https://github.com/mbzuai-oryx/AIN
공식 코드https://github.com/mbzuai-oryx/CAMEL-Bench
공식 코드https://github.com/mbzuai-oryx/video-chatgpt
공식 코드Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
https://github.com/mbzuai-oryx/video-llava
공식 코드https://github.com/mbzuai-oryx/videogpt-plus
공식 코드VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
https://github.com/mcg-nju/basictad
공식 코드BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
https://github.com/mcg-nju/ddm
공식 코드Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection
https://github.com/mcg-nju/mmn
공식 코드Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
https://github.com/mcg-nju/sportshhi
공식 코드SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos
https://github.com/md-mohaiminul/ViS4mer
공식 코드Long Movie Clip Classification with State-Space Video Models
https://github.com/md-mohaiminul/VideoRecap
공식 코드https://github.com/mdivyanshu97/discovr
공식 코드Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
https://github.com/mettyz/ssvc
공식 코드https://github.com/microsoft/p.910
공식 코드https://github.com/microsoft/swinbert
공식 코드SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning
https://github.com/midas-research/video-persuasion
공식 코드A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot
https://github.com/mindspore-lab/models
공식 코드No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
https://github.com/minghchen/carl_code
공식 코드Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
https://github.com/mininglamp-mllm/hmllm
공식 코드https://github.com/mit-han-lab/x-attention
공식 코드XAttention: Block Sparse Attention with Antidiagonal Scoring
https://github.com/mlvlab/vidchain
공식 코드VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
https://github.com/mnyuew/metok
공식 코드METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
https://github.com/modelscope/data-juicer
공식 코드https://github.com/mohitsharma29/NoisyActions2M
공식 코드NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels
https://github.com/moohnai/mofo
공식 코드MOFO: MOtion FOcused Self-Supervision for Video Understanding
https://github.com/mpekalski/Y8M
공식 코드Deep Learning Methods for Efficient Large Scale Video Labeling
https://github.com/msu-video-group/erqa
공식 코드ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution
https://github.com/msu-video-group/msu_vqm_compression_benchmark
공식 코드Video compression dataset and benchmark of learning-based video-quality metrics
https://github.com/mttr2021/MTTR
공식 코드End-to-End Referring Video Object Segmentation with Multimodal Transformers
https://github.com/mu-cai/TemporalBench
공식 코드TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
https://github.com/multimodal-art-projection/iv-bench
공식 코드IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
https://github.com/multimodal-art-projection/scalelong
공식 코드ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.