https://github.com/TeCSAR-UNCC/CARPe_Posterum
공식 코드CARPe Posterum: A Convolutional Approach for Real-time Pedestrian Path Prediction
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/TencentARC/ST-LLM
공식 코드ST-LLM: Large Language Models Are Effective Temporal Learners
https://github.com/TencentYoutuResearch/ActionDetection-AFSD
공식 코드Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
https://github.com/The-Martyr/OccludeNet-Dataset
공식 코드OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions
https://github.com/TheShadow29/VidSitu
공식 코드https://github.com/Thinksky5124/SVTAS
공식 코드https://github.com/TooTouch/REVECA
공식 코드REVECA -- Rich Encoder-decoder framework for Video Event CAptioner
https://github.com/Tsingularity/youtube-8m
공식 코드Hierarchical Deep Recurrent Architecture for Video Understanding
https://github.com/UTAustin-SwarmLab/NeuS-V
공식 코드Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification
https://github.com/UTAustin-SwarmLab/Neuro-Symbolic-Video-Search-Temporal-Logic
공식 코드https://github.com/VITA-MLLM/Sparrow
공식 코드T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs
https://github.com/VideoNetworks/TokShift-Transformer
공식 코드https://github.com/Vincent-ZHQ/LV-LLMs
공식 코드https://github.com/Vision-CAIR/InfiniBench
공식 코드InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding
https://github.com/Vision-CAIR/LongVU
공식 코드LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
https://github.com/Vision-CAIR/MiniGPT4-video
공식 코드https://github.com/VisionLearningGroup/JEDDi-Net
공식 코드Joint Event Detection and Description in Continuous Video Streams
https://github.com/WenxuanZhu1103/4D-Bench
공식 코드4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding
https://github.com/Whiffe/Custom-ava-dataset_Custom-Spatio-Temporally-Action-Video-Dataset
공식 코드A Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions
https://github.com/WuJie1010/TSP-PRL
공식 코드https://github.com/XenonLamb/EditVid-QA
공식 코드Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model
https://github.com/Yui010206/MoPRL
공식 코드Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
https://github.com/Ziyang412/VideoTree
공식 코드VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
https://github.com/aHapBean/VideoREPA
공식 코드VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
https://github.com/abhijay9/shifttolerant-lpips
공식 코드https://github.com/adap/flower
공식 코드https://github.com/adityavavre/videgovlm
공식 코드EgoVLM: Policy Optimization for Egocentric Video Understanding
https://github.com/agao8/STEAD
공식 코드STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications
https://github.com/aghdamamir/actalign
공식 코드ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment
https://github.com/ahmad-573/vurf
공식 코드VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding
https://github.com/aimagelab/Consistency-based-Self-supervised-Learning-for-Temporal-Anomaly-Localization
공식 코드Consistency-based Self-supervised Learning for Temporal Anomaly Localization
https://github.com/aimagelab/STAGE_action_detection
공식 코드Video action detection by learning graph-based spatio-temporal interactions
https://github.com/airsplay/vimpac
공식 코드VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
https://github.com/alanaai/evud
공식 코드AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding
https://github.com/alexandrosstergiou/Leaping-Into-Memories
공식 코드https://github.com/alibaba-mmai-research/TAdaConv
공식 코드Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.