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.
VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation
Teaching VLMs to Localize Specific Objects from In-context Examples
Principles of Visual Tokens for Efficient Video Understanding
Extending Video Masked Autoencoders to 128 frames
DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding
AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models
Can MLLMs Guide Weakly-Supervised Temporal Action Localization Tasks?
Weakly-Supervised Anomaly Detection in Surveillance Videos Based on Two-Stream I3D Convolution Network
EVQAScore: Efficient Video Question Answering Data Evaluation
Video RWKV:Video Action Recognition Based RWKV
StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
VQA$^2$: Visual Question Answering for Video Quality Assessment
Personalized Video Summarization by Multimodal Video Understanding
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
Video Token Merging for Long-form Video Understanding
Situational Scene Graph for Structured Human-centric Situation Understanding
TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models
Deep Priors for Video Quality Prediction
Zero-Shot Action Recognition in Surveillance Videos
Egocentric and Exocentric Methods: A Short Survey
Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
CAMEL-Bench: A Comprehensive Arabic LMM Benchmark
VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning
ContextDet: Temporal Action Detection with Adaptive Context Aggregation
EVA: An Embodied World Model for Future Video Anticipation
Making Every Frame Matter: Continuous Video Understanding for Large Models via Adaptive State Modeling
Zero-shot Action Localization via the Confidence of Large Vision-Language Models
Latent Image and Video Resolution Prediction using Convolutional Neural Networks
VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.