Charades-STA
Emerging14papers using it
2020first seen
The 'Charades-STA' dataset is a benchmark used to evaluate temporal reasoning in long videos by providing a collection of videos annotated with natural language queries and corresponding temporal segments.
Papers using Charades-STA (14)
- VideoLoom: A Video Large Language Model for Joint Spatial-Temporal UnderstandingChrono: A Simple Blueprint for Representing Time in MLLMsTimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily LivingXiaomi Mimo-vl-miloco Technical ReportSee More, Store Less: Memory-Efficient Resolution for Video Moment RetrievalLanguage-guided Temporal Token Pruning For Efficient Videollm ProcessingMLVTG: Mamba-based Feature Alignment And Llm-driven Purification For Multi-modal Video Temporal GroundingWeakly Supervised Temporal Adjacent Network for Language GroundingEnd-to-end Multi-modal Video Temporal GroundingFine-grained Iterative Attention Network for TemporalLanguage
Localization in VideosLearning Modality Interaction for Temporal Sentence Localization and
Event Captioning in VideosRelation-aware Video Reading Comprehension for Temporal Language
GroundingReducing the Vision and Language Bias for Temporal Sentence GroundingTemporal Insight Enhancement: Mitigating Temporal Hallucination in
Multimodal Large Language Models