Related papers: Spatio-temporal Video Re-localization by Warp LSTM
Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long…
We propose a new task of space-time semantic correspondence prediction in videos. Given a source video, a target video, and a set of space-time key-points in the source video, the task requires predicting a set of keypoints in the target…
The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features…
Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning…
Typical person re-identification frameworks search for k best matches in a gallery of images that are often collected in varying conditions. The gallery may contain image sequences when re-identification is done on videos. However, such a…
This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to…
Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically…
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture…
We describe a new spatio-temporal video autoencoder, based on a classic spatial image autoencoder and a novel nested temporal autoencoder. The temporal encoder is represented by a differentiable visual memory composed of convolutional long…
Spatio-Temporal Video Grounding (STVG) aims to localize a spatio-temporal tube that corresponds to a given language query in an untrimmed video. This is a challenging task since it involves complex vision-language understanding and…
Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant moment in an untrimmed video, and 2) bridging the semantic gap…
Recently, the Transformer module has been transplanted from natural language processing to computer vision. This paper applies the Transformer to video-based person re-identification, where the key issue is to extract the discriminative…
Object proposals for detecting moving or static video objects need to address issues such as speed, memory complexity and temporal consistency. We propose an efficient Video Object Proposal (VOP) generation method and show its efficacy in…
Self-supervised audio-visual learning aims to capture useful representations of video by leveraging correspondences between visual and audio inputs. Existing approaches have focused primarily on matching semantic information between the…
Millions of surveillance cameras operate at 24x7 generating huge amount of visual data for processing. However, retrieval of important activities from such a large data can be time consuming. Thus, researchers are working on finding…
We retarget video stitching to an emerging issue, named warping shake, which unveils the temporal content shakes induced by sequentially unsmooth warps when extending image stitching to video stitching. Even if the input videos are stable,…
We present RELOCATE, a simple training-free baseline designed to perform the challenging task of visual query localization in long videos. To eliminate the need for task-specific training and efficiently handle long videos, RELOCATE…
Weakly-supervised temporal action localization aims to identify and localize the action instances in the untrimmed videos with only video-level action labels. When humans watch videos, we can adapt our abstract-level knowledge about actions…
We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…
Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle…