Related papers: MVFNet: Multi-View Fusion Network for Efficient Vi…
Evaluation is essential in image fusion research, yet most existing metrics are directly borrowed from other vision tasks without proper adaptation. These traditional metrics, often based on complex image transformations, not only fail to…
Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets…
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been…
We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to…
Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To…
Due to the problem of performance constraints of unsupervised video object detection, its large-scale application is limited. In response to this pain point, we propose another excellent method to solve this problematic point. By…
In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the…
We investigate video classification via a two-stream convolutional neural network (CNN) design that directly ingests information extracted from compressed video bitstreams. Our approach begins with the observation that all modern video…
RGB-T semantic segmentation has been widely adopted to handle hard scenes with poor lighting conditions by fusing different modality features of RGB and thermal images. Existing methods try to find an optimal fusion feature for…
Video super-resolution (VSR) is a task that aims to reconstruct high-resolution (HR) frames from the low-resolution (LR) reference frame and multiple neighboring frames. The vital operation is to utilize the relative misaligned frames for…
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including challenges like composite action, and co-occurring action.…
The recent advances in Convolutional Neural Networks (CNNs) and Vision Transformers have convincingly demonstrated high learning capability for video action recognition on large datasets. Nevertheless, deep models often suffer from the…
Applying salient object detection (SOD) to RGB-D videos is an emerging task called RGB-D VSOD and has recently gained increasing interest, due to considerable performance gains of incorporating motion and depth and that RGB-D videos can be…
In the study, we present AMFusionNet, an innovative approach to infrared and visible image fusion (IVIF), harnessing the power of multiple kernel sizes and attention mechanisms. By assimilating thermal details from infrared images with…
Video prediction is a pixel-level task that generates future frames by employing the historical frames. There often exist continuous complex motions, such as object overlapping and scene occlusion in video, which poses great challenges to…
Effective extraction of temporal patterns is crucial for the recognition of temporally varying actions in video. We argue that the fixed-sized spatio-temporal convolution kernels used in convolutional neural networks (CNNs) can be improved…
Human video motion transfer (HVMT) aims to synthesize videos that one person imitates other persons' actions. Although existing GAN-based HVMT methods have achieved great success, they either fail to preserve appearance details due to the…
Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels…
Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost…
Deepfake media is becoming widespread nowadays because of the easily available tools and mobile apps which can generate realistic looking deepfake videos/images without requiring any technical knowledge. With further advances in this field…