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.
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
https://arxiv.org/abs/2407.00634
Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds
InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding
Snakes and Ladders: Two Steps Up for VideoMamba
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads
Zero-Shot Long-Form Video Understanding through Screenplay
Priorformer: A UGC-VQA Method with content and distortion priors
VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer
PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models
VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation
Towards Event-oriented Long Video Understanding
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
GVT2RPM: An Empirical Study for General Video Transformer Adaptation to Remote Physiological Measurement
AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding
Towards Holistic Language-video Representation: the language model-enhanced MSR-Video to Text Dataset
Slot State Space Models
DrVideo: Document Retrieval Based Long Video Understanding
VideoVista: A Versatile Benchmark for Video Understanding and Reasoning
Hallucination Mitigation Prompts Long-term Video Understanding
VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment
Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model
GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding
Localizing Events in Videos with Multimodal Queries
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
LVBench: An Extreme Long Video Understanding Benchmark
Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.