Related papers: Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2…
Visual tempo, which describes how fast an action goes, has shown its potential in supervised action recognition. In this work, we demonstrate that visual tempo can also serve as a self-supervision signal for video representation learning.…
This paper presents a comprehensive evaluation of lightweight deep learning models for image classification, emphasizing their suitability for deployment in resource-constrained environments such as low-memory devices. Five state-of-the-art…
The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal action localization…
We present a new data-driven video inpainting method for recovering missing regions of video frames. A novel deep learning architecture is proposed which contains two sub-networks: a temporal structure inference network and a spatial detail…
Video action analysis is a foundational technology within the realm of intelligent video comprehension, particularly concerning its application in Internet of Things(IoT). However, existing methodologies overlook feature semantics in…
Video-based Visible-Infrared person re-identification (VVI-ReID) aims to retrieve the same pedestrian across visible and infrared modalities from video sequences. Existing methods tend to exploit modality-invariant visual features but…
Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as…
Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness for industrial visual inspection remains unclear. Industrial data differ substantially…
The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition using contrastive learning. However, learning effective representations for skeleton-based…
Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for learning transferable features. In particular, Image-based Joint-Embedding Predictive…
World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM),…
For deepfake detection, video-level detectors have not been explored as extensively as image-level detectors, which do not exploit temporal data. In this paper, we empirically show that existing approaches on image and sequence classifiers…
Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human…
Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…
We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…
Pixel space augmentation has grown in popularity in many Deep Learning areas, due to its effectiveness, simplicity, and low computational cost. Data augmentation for videos, however, still remains an under-explored research topic, as most…
A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video…
A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video…
While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of…
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features…