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/pavancm/contrique
공식 코드https://github.com/pavancm/conviqt
공식 코드https://github.com/piergiaj/representation-flow-cvpr19
공식 코드https://github.com/pku-alignment/safe-sora
공식 코드SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
https://github.com/pku-yuangroup/chat-univi
공식 코드https://github.com/pkunlp-icler/fastv
공식 코드https://github.com/pomonam/LearnablePoolingMethods
공식 코드https://github.com/postech-ami/smile-dataset
공식 코드SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models
https://github.com/prashnani/PerceptualImageError
공식 코드PieAPP: Perceptual Image-Error Assessment through Pairwise Preference
https://github.com/princetonvisualai/merv
공식 코드Unifying Specialized Visual Encoders for Video Language Models
https://github.com/pritamqu/vcrbench
공식 코드VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models
https://github.com/pytorch/fairseq
공식 코드VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
https://github.com/q-future/q-align
공식 코드Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
https://github.com/q-future/visual-question-answering-for-video-quality-assessment
공식 코드VQA$^2$: Visual Question Answering for Video Quality Assessment
https://github.com/qmme/stablevqa
공식 코드StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability
https://github.com/qmme/t2vqa
공식 코드Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment
https://github.com/qq-mm/video-ccam
공식 코드https://github.com/qualityassessment/bvqi
공식 코드Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion
https://github.com/qyp2000/kvq
공식 코드KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception
https://github.com/qzhb/bssard
공식 코드https://github.com/raghavgoyal14/minotaur/tree/rgv/all-tasks
공식 코드MINOTAUR: Multi-task Video Grounding From Multimodal Queries
https://github.com/rd20karim/synch-transformer
공식 코드Transformer with Controlled Attention for Synchronous Motion Captioning
https://github.com/renjie-liang/emet
공식 코드Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation
https://github.com/renshuhuai-andy/timechat
공식 코드TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
https://github.com/rese1f/MovieChat
공식 코드MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
https://github.com/richermans/AudioCaption
공식 코드https://github.com/richzhang/PerceptualSimilarity
공식 코드The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
https://github.com/riotu-lab/DrifNet
공식 코드DriftNet: Aggressive Driving Behavior Classification using 3D EfficientNet Architecture
https://github.com/rucaibox/event-bench
공식 코드https://github.com/rupertluo/valley
공식 코드Valley: Video Assistant with Large Language model Enhanced abilitY
https://github.com/sais-fuxi/omni-video
공식 코드Omni-Video: Democratizing Unified Video Understanding and Generation
https://github.com/sakibreza/eccv24-hat
공식 코드HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization
https://github.com/salesforce/paprika
공식 코드Procedure-Aware Pretraining for Instructional Video Understanding
https://github.com/santiagosilas/mc-vad-dataset-basedon-pets2009
공식 코드A MIL Approach for Anomaly Detection in Surveillance Videos from Multiple Camera Views
https://github.com/sapeirone/hier-egopack
공식 코드Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.