Charades-STA
PulseAugur coverage of Charades-STA — every cluster mentioning Charades-STA across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Moment-GPT pipeline uses Llama 3 for zero-shot video moment retrieval
Researchers have introduced Moment-GPT, a novel pipeline designed for zero-shot video moment retrieval that leverages existing multimodal large language models (MLLMs) without requiring fine-tuning. This approach aims t…
-
New IAE-VTG method improves action-entity video temporal grounding
Researchers have introduced IAE-VTG, a novel approach to Video Temporal Grounding (VTG) that specifically addresses queries involving actions performed by entities. Unlike previous methods that treat queries holisticall…
-
New method improves VLM temporal grounding by asking binary questions
Researchers have developed a novel training-free method called FV-Action for temporal grounding in vision-language models (VLMs). This approach addresses the issue of VLMs confidently providing incorrect timestamps for …
-
New REZE method enhances video temporal grounding accuracy
Researchers have developed REZE, a novel training-free method for video temporal grounding that improves accuracy by splitting videos into clips and assessing query relevance at the clip level. This approach bypasses di…
-
TimeProVe framework enhances long video temporal reasoning with efficient verification
Researchers have developed TimeProVe, a novel framework designed to improve the efficiency of temporal reasoning in long videos. This approach uses lightweight modules to propose potential answers and evidence, only eng…
-
New SMART framework enhances video moment retrieval with audio and shot-aware compression
Researchers have developed SMART, a new framework for video moment retrieval that enhances multimodal understanding by integrating audio cues with visual information. This approach utilizes a Multimodal Large Language M…
-
New framework CoSTL enhances video moment retrieval and highlight detection
Researchers have introduced CoSTL, a new framework designed to improve video moment retrieval and highlight detection. This approach addresses limitations in existing methods by focusing on both fine-grained image-level…
-
GIRL-DETR enhances video moment retrieval with reinforcement learning
Researchers have developed GIRL-DETR, a novel approach to improve video moment retrieval by addressing optimization challenges in lightweight models. This method freezes the backbone network after supervised training an…
-
New network transfers knowledge for unsupervised video-text matching
Researchers have developed a novel cross-modal knowledge transfer network for unsupervised temporal sentence grounding. This approach aims to overcome the reliance on expensive, paired video-query annotations by leverag…
-
New AI approach uses game theory for video temporal grounding
Researchers have introduced a novel approach to weakly-supervised video temporal grounding by framing the problem from a game theory perspective. This new method addresses limitations in existing models, such as coarse-…
-
AdaFocus framework boosts long video understanding with adaptive sampling
Researchers have developed AdaFocus, a new framework designed to improve the efficiency of understanding long videos. This method avoids the high costs of dense encoding or the information loss from aggressive compressi…