Related papers: BSUV-Net 2.0: Spatio-Temporal Data Augmentations f…
Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data. Different from existing works, we present a…
Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned…
Recently, 3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it encounters challenges for high-resolution novel view synthesis (HRNVS) due to the…
As a very common type of video, face videos often appear in movies, talk shows, live broadcasts, and other scenes. Real-world online videos are often plagued by degradations such as blurring and quantization noise, due to the high…
Bit-level sparsity methods skip ineffectual zero-bit operations and are typically applicable within bit-serial deep learning accelerators. This type of sparsity at the bit-level is especially interesting because it is both orthogonal and…
Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods. However, existing data-driven approaches heavily rely on a large…
Temporal sentence grounding in videos (TSGV) faces challenges due to public TSGV datasets containing significant temporal biases, which are attributed to the uneven temporal distributions of target moments. Existing methods generate…
Self-supervised denoising has attracted widespread attention due to its ability to train without clean images. However, noise in real-world scenarios is often spatially correlated, which causes many self-supervised algorithms that assume…
Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…
Continuous space-time video super-resolution (C-STVSR) has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary spatial and temporal scales. However, prevailing methods often…
The task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to…
Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP). To address this issue, we develop an effective spatiotemporal…
Deep learning has made significant strides in video understanding tasks, but the computation required to classify lengthy and massive videos using clip-level video classifiers remains impractical and prohibitively expensive. To address this…
Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we reduce this cost by exploiting the fact that the importance of features computed by…
Multi-view 3D reconstruction remains a core challenge in computer vision. Recent methods, such as DUST3R and its successors, directly regress pointmaps from image pairs without relying on known scene geometry or camera parameters. However,…
Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might…
Taking advantage of human pose data for understanding human activities has attracted much attention these days. However, state-of-the-art pose estimators struggle in obtaining high-quality 2D or 3D pose data due to occlusion, truncation and…
Recent advances in supervised deep learning methods are enabling remote measurements of photoplethysmography-based physiological signals using facial videos. The performance of these supervised methods, however, are dependent on the…
Novel view synthesis (NVS) is increasingly relevant for edge robotics, where compact and incrementally updatable 3D scene models are needed for SLAM, navigation, and inspection under tight memory and latency budgets. Variational Bayesian…
Gaze is an essential prompt for analyzing human behavior and attention. Recently, there has been an increasing interest in determining gaze direction from facial videos. However, video gaze estimation faces significant challenges, such as…