Related papers: Correlation-Guided Query-Dependency Calibration fo…
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many…
To generate proper captions for videos, the inference needs to identify relevant concepts and pay attention to the spatial relationships between them as well as to the temporal development in the clip. Our end-to-end encoder-decoder video…
Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot…
Video moment retrieval (MR) and highlight detection (HD) based on natural language queries are two highly related tasks, which aim to obtain relevant moments within videos and highlight scores of each video clip. Recently, several methods…
Temporal grounding entails establishing a correspondence between natural language event descriptions and their visual depictions. Compositional modeling becomes central: we first ground atomic descriptions "girl eating an apple," "batter…
While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a…
Video representation learning has been successful in video-text pre-training for zero-shot transfer, where each sentence is trained to be close to the paired video clips in a common feature space. For long videos, given a paragraph of…
Motivated by the success of coarse-grained or fine-grained contrast in text-video retrieval, there emerge multi-grained contrastive learning methods which focus on the integration of contrasts with different granularity. However, due to the…
Text-guided Video Temporal Grounding (VTG) aims to localize relevant segments in untrimmed videos based on textual descriptions, encompassing two subtasks: Moment Retrieval (MR) and Highlight Detection (HD). Although previous typical…
Video Paragraph Grounding (VPG) aims to precisely locate the most appropriate moments within a video that are relevant to a given textual paragraph query. However, existing methods typically rely on large-scale annotated temporal labels and…
Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence…
Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-scale video-based models incurs considerably higher costs…
With the increasing demand for video understanding, video moment and highlight detection (MHD) has emerged as a critical research topic. MHD aims to localize all moments and predict clip-wise saliency scores simultaneously. Despite progress…
Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding. Existing works attempt to progressively narrow the search…
Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models,…
Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. Since datasets in this domain are often gathered from limited video scenes, models tend to…
Video temporal grounding (VTG) is typically tackled with dataset-specific models that transfer poorly across domains and query styles. Recent efforts to overcome this limitation have adapted large multimodal language models (MLLMs) to VTG,…
Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on…
We present a general approach to video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a video to be a 1D sequence of clips, each one associated with its…
Temporal grounding aims to retrieve moments of the described event within an untrimmed video by a language query. Typically, existing methods assume annotations are precise and unique, yet one query may describe multiple moments in many…