Zero-shot Moment Retrieval
1개 벤치마크 · 논문 4편 · 이 태스크의 논문 보기 →
Benchmarks
QVHighlights
Most implemented
Saliency-Guided DETR for Moment Retrieval and Highlight Detection
VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT
Papers
VeRVE: Versatile Retrieval for Videos via Unified Embeddings
Modern video retrieval systems are expected to handle diverse tasks ranging from corpus-level retrieval, fine-grained moment localization to flexible multimodal querying. Specialized architectures achieve strong retrieva…
Zero-shot Moment RetrievalZero-Shot Video RetrievalPoint to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos
Zero-shot Long Video Moment Retrieval (ZLVMR) is the task of identifying temporal segments in hour-long videos using a natural language query without task-specific training. The core technical challenge of LVMR stems fro…
Zero-shot Moment RetrievalSaliency-Guided DETR for Moment Retrieval and Highlight Detection
Existing approaches for video moment retrieval and highlight detection are not able to align text and video features efficiently, resulting in unsatisfying performance and limited production usage. To address this, we pr…
Highlight DetectionMoment RetrievalNatural Language Moment RetrievalNatural Language Queries+3VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT
Video temporal grounding (VTG) aims to locate specific temporal segments from an untrimmed video based on a linguistic query. Most existing VTG models are trained on extensive annotated video-text pairs, a process that n…
Image CaptioningZero-shot Moment Retrieval