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.
TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
ViFi-ReID: A Two-Stream Vision-WiFi Multimodal Approach for Person Re-identification
Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering
Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities
VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
TVBench: Redesigning Video-Language Evaluation
Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content
Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization
Secure Video Quality Assessment Resisting Adversarial Attacks
MM-Ego: Towards Building Egocentric Multimodal LLMs
TRACE: Temporal Grounding Video LLM via Causal Event Modeling
T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design
Enhancing Temporal Modeling of Video LLMs via Time Gating
MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
Frame-Voyager: Learning to Query Frames for Video Large Language Models
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM
AirLetters: An Open Video Dataset of Characters Drawn in the Air
UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark
Deep learning for action spotting in association football videos
ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding
Visual Context Window Extension: A New Perspective for Long Video Understanding
Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs
VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
Delving Deep into Engagement Prediction of Short Videos
From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding
EAGLE: Egocentric AGgregated Language-video Engine
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
LLM4Brain: Training a Large Language Model for Brain Video Understanding
E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
Revisiting Video Quality Assessment from the Perspective of Generalization
Advancing Video Quality Assessment for AIGC
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.