Natural Language Moment Retrieval
12 papers with code • 4 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Natural Language Moment Retrieval
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
ActivityNet Captions
DiDeMo
MAD
Most implemented papers
Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding
wjun0830/cgdetr
•
•
Dummy tokens conditioned by text query take portions of the attention weights, preventing irrelevant video clips from being represented by the text query.
Dense Regression Network for Video Grounding
The key idea of this paper is to use the distances between the frame within the ground truth and the starting (ending) frame as dense supervisions to improve the video grounding accuracy.
VLG-Net: Video-Language Graph Matching Network for Video Grounding
Soldelli/VLG-Net
•
•
Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query.
MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions
The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques.
Localizing Moments in Long Video Via Multimodal Guidance
waybarrios/guidance-based-video-grounding
•
•
ICCV 2023
In this paper, we propose a method for improving the performance of natural language grounding in long videos by identifying and pruning out non-describable windows.
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
zjr2000/gvl
•
•
Our framework is easily extensible to tasks covering visually-grounded language understanding and generation.
Overcoming Weak Visual-Textual Alignment for Video Moment Retrieval
Video moment retrieval (VMR) identifies a specific moment in an untrimmed video for a given natural language query.
UniVTG: Towards Unified Video-Language Temporal Grounding
Most methods in this direction develop taskspecific models that are trained with type-specific labels, such as moment retrieval (time interval) and highlight detection (worthiness curve), which limits their abilities to generalize to various VTG tasks and labels.
UnLoc: A Unified Framework for Video Localization Tasks
google-research/scenic
•
•
ICCV 2023
While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task.
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
Video Moment Retrieval (MR) and Highlight Detection (HD) have attracted significant attention due to the growing demand for video analysis.
