Related papers: Video Task Decathlon: Unifying Image and Video Tas…
Bird's-Eye-View (BEV) perception has become a vital component of autonomous driving systems due to its ability to integrate multiple sensor inputs into a unified representation, enhancing performance in various downstream tasks. However,…
LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios. However, existing multi-modal methods face two key…
Video-Based Design (VBD) uses video as a primary medium for analyzing user interactions, prototyping, and generating design insights. However, current VBD workflows are constrained by labor-intensive, inconsistent manual annotations that…
Comprehensive testing of autonomous systems through simulation is essential to ensure the safety of autonomous driving vehicles. This requires the generation of safety-critical scenarios that extend beyond the limitations of real-world data…
Deep convolutional neural networks (CNNs) have been shown to perform extremely well at a variety of tasks including subtasks of autonomous driving such as image segmentation and object classification. However, networks designed for these…
Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field has achieved remarkable progress in recent years, further…
Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this…
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contributing factor is that natural image datasets provide limited supervision for low-level…
In computer vision, an entity such as an image or video is often represented as a set of instance vectors, which can be SIFT, motion, or deep learning feature vectors extracted from different parts of that entity. Thus, it is essential to…
Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…
Unlike humans, who can effortlessly estimate the entirety of objects even when partially occluded, modern computer vision algorithms still find this aspect extremely challenging. Leveraging this amodal perception for autonomous driving…
Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of…
Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…
Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with…
In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world has a great demand for labor and money…
Vision language decision making (VLDM) is a challenging multimodal task. The agent have to understand complex human instructions and complete compositional tasks involving environment navigation and object manipulation. However, the long…
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem…
Video Salient Document Detection (VSDD) is an essential task of practical computer vision, which aims to highlight visually salient document regions in video frames. Previous techniques for VSDD focus on learning features without…
Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…
General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D…