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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Towards Long Video Understanding via Fine-detailed Video Story Generation
Espresso: High Compression For Rich Extraction From Videos for Your Vision-Language Model
Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection
LinVT: Empower Your Image-level Large Language Model to Understand Videos
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
VisionZip: Longer is Better but Not Necessary in Vision Language Models
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
Streaming Detection of Queried Event Start
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
Video Quality Assessment: A Comprehensive Survey
Progress-Aware Video Frame Captioning
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback
HunyuanVideo: A Systematic Framework For Large Video Generative Models
SEAL: Semantic Attention Learning for Long Video Representation
PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos
Towards Universal Soccer Video Understanding
VideoSAVi: Self-Aligned Video Language Models without Human Supervision
VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
Subjective and Objective Quality Assessment Methods of Stereoscopic Videos with Visibility Affecting Distortions
LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos
Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark
T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs
STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM
SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context
Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric
OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions
ReWind: Understanding Long Videos with Instructed Learnable Memory
VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement
Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.