Related papers: Diversifying Spatial-Temporal Perception for Video…

In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first…

We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…

In this paper, we propose a novel SpatioTemporal convolutional Dense Network (STDNet) to address the video-based crowd counting problem, which contains the decomposition of 3D convolution and the 3D spatiotemporal dilated dense convolution…

Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably…

The task of video prediction is forecasting the next frames given some previous frames. Despite much recent progress, this task is still challenging mainly due to high nonlinearity in the spatial domain. To address this issue, we propose a…

Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning…

As one of the prominent AI-generated content, Deepfake has raised significant safety concerns. Although it has been demonstrated that temporal consistency cues offer better generalization capability, existing methods based on CNNs…

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…

Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts…

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…

3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…

Domain generalization (DG) focuses on transferring domain-invariant knowledge from multiple source domains (available at train time) to an, a priori, unseen target domain(s). This requires a class to be expressed in multiple domains for the…

Unsupervised video domain adaptation is a practical yet challenging task. In this work, for the first time, we tackle it from a disentanglement view. Our key idea is to handle the spatial and temporal domain divergence separately through…

We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models such that a non-expert user can define a new task depending on their needs via a few labeled examples and minimal domain…

Single-domain generalization aims to learn a model from single source domain data to achieve generalized performance on other unseen target domains. Existing works primarily focus on improving the generalization ability of static networks.…

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…

Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial…

A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task,…

Video-based person re-identification matches video clips of people across non-overlapping cameras. Most existing methods tackle this problem by encoding each video frame in its entirety and computing an aggregate representation across all…

Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and…