Papers with Code 아카이브
Video Grounding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 2
- 보존된 평가 기록
- 9
Video grounding is the task of linking spoken language descriptions to specific video segments. In video grounding, the model is given a video and a natural language description, such as a sentence or a caption, and its goal is to identify the specific segment of the video that corresponds to the description. This can involve tasks such as localizing the objects or actions mentioned in the description within the video, or associating a specific time interval with the description.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
Object-Shot Enhanced Grounding Network for Egocentric Video
Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection
VideoGEM: Training-free Action Grounding in Videos
SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability
TimeZero: Temporal Video Grounding with Reasoning-Guided LVLM
OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding
TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos
Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding
Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
Consistency of Compositional Generalization across Multiple Levels
Multi-Scale Contrastive Learning for Video Temporal Grounding
Video LLMs for Temporal Reasoning in Long Videos
VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding
SimBase: A Simple Baseline for Temporal Video Grounding
Transformer with Controlled Attention for Synchronous Motion Captioning
SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
Multi-sentence Video Grounding for Long Video Generation
Described Spatial-Temporal Video Detection
AutoTVG: A New Vision-language Pre-training Paradigm for Temporal Video Grounding
Simplify Implant Depth Prediction as Video Grounding: A Texture Perceive Implant Depth Prediction Network
Artemis: Towards Referential Understanding in Complex Videos
Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
SnAG: Scalable and Accurate Video Grounding
SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding
HawkEye: Training Video-Text LLMs for Grounding Text in Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.