Related papers: Circulant temporal encoding for video retrieval an…
Dense event captioning aims to detect and describe all events of interest contained in a video. Despite the advanced development in this area, existing methods tackle this task by making use of dense temporal annotations, which is…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
We introduce VideoComp, a benchmark and learning framework for advancing video-text compositionality understanding, aimed at improving vision-language models (VLMs) in fine-grained temporal alignment. Unlike existing benchmarks focused on…
Applying image processing algorithms independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our…
While video compression algorithms effectively reduce bitrate, aggressive quantization often compromises temporal coherence, introducing artifacts such as flicker, motion inconsistency, and unstable textures. Although spatial quality…
Video moment retrieval (VMR) identifies a specific moment in an untrimmed video for a given natural language query. This task is prone to suffer the weak alignment problem innate in video datasets. Due to the ambiguity, a query does not…
Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part…
Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations…
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…
A major focus of current research on place recognition is visual localization for autonomous driving. In this scenario, as cameras will be operating continuously, it is realistic to expect videos as an input to visual localization…
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…
We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we…
In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a…
Although the problem of automatic video summarization has recently received a lot of attention, the problem of creating a video summary that also highlights elements relevant to a search query has been less studied. We address this problem…
We are concerned with retrieving a query person from multiple videos captured by a non-overlapping camera network. Existing methods often rely on purely visual matching or consider temporal constraints but ignore the spatial information of…
Recently, deep learning approach, especially deep Convolutional Neural Networks (ConvNets), have achieved overwhelming accuracy with fast processing speed for image classification. Incorporating temporal structure with deep ConvNets for…
This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an…
Large video-language models (LVLMs) have shown remarkable performance across various video-language tasks. However, they encounter significant challenges when processing long videos because of the large number of video frames involved.…
State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspondences across videos in time. They either learn frame-to-frame mapping across sequences, which does not leverage temporal…
Video Moment Retrieval (VMR) aims to retrieve relevant moments of an untrimmed video corresponding to the query. While cross-modal interaction approaches have shown progress in filtering out query-irrelevant information in videos, they…