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.
Two Causally Related Needles in a Video Haystack
AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs
Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding
Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles
Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
Leveraging Foundation Models for Multimodal Graph-Based Action Recognition
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning
Clapper: Compact Learning and Video Representation in VLMs
ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation
CP-LLM: Context and Pixel Aware Large Language Model for Video Quality Assessment
A Challenge to Build Neuro-Symbolic Video Agents
Domain Adaptation of VLM for Soccer Video Understanding
LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts
Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation
Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding
From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations
LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
Semantically-Aware Game Image Quality Assessment
VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models
SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation
Gameplay Highlights Generation
DAPE: Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Video Editing with Diffusion Models
Seed1.5-VL Technical Report
Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining
StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.