Related papers: Video Task Decathlon: Unifying Image and Video Tas…

In this work, we aim to learn a unified vision-based policy for multi-fingered robot hands to manipulate a variety of objects in diverse poses. Though prior work has shown benefits of using human videos for policy learning, performance…

Federated Learning (FL) is a distributed learning paradigm that can learn a global or personalized model from decentralized datasets on edge devices. However, in the computer vision domain, model performance in FL is far behind centralized…

Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to…

Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protected…

Mobile robots are increasingly required to navigate and interact within unknown and unstructured environments to meet human demands. Demand-driven navigation (DDN) enables robots to identify and locate objects based on implicit human…

Visual recognition algorithms are required today to exhibit adaptive abilities. Given a deep model trained on a specific, given task, it would be highly desirable to be able to adapt incrementally to new tasks, preserving scalability as the…

Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To…

Self-driving technology is advancing rapidly --- albeit with significant challenges and limitations. This progress is largely due to recent developments in deep learning algorithms. To date, however, there has been no systematic comparison…

LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a…

When humans perceive the world, they naturally integrate multiple audio-visual tasks within dynamic, real-world scenes. However, current works such as event localization, parsing, segmentation and question answering are mostly explored…

Visual perspective taking (VPT) is the ability to perceive and reason about the perspectives of others. It is an essential feature of human intelligence, which develops over the first decade of life and requires an ability to process the 3D…

By leveraging large amounts of product data collected across hundreds of live e-commerce websites, we construct 1000 unique classification tasks that share similarly-structured input data, comprised of both text and images. These…

Many recent medical segmentation systems rely on powerful deep learning models to solve highly specific tasks. To maximize performance, it is standard practice to evaluate numerous pipelines with varying model topologies, optimization…

Rearrangement tasks have been identified as a crucial challenge for intelligent robotic manipulation, but few methods allow for precise construction of unseen structures. We propose a visual foresight model for pick-and-place rearrangement…

Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning. While vision-only autonomous driving methods have recently achieved notable performance, through enhanced…

Nowadays, distributed smart cameras are deployed for a wide set of tasks in several application scenarios, ranging from object recognition, image retrieval, and forensic applications. Due to limited bandwidth in distributed systems,…

This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision,…

This paper presents VTN, a transformer-based framework for video recognition. Inspired by recent developments in vision transformers, we ditch the standard approach in video action recognition that relies on 3D ConvNets and introduce a…

State-of-the-art approaches for autonomous driving integrate multiple sub-tasks of the overall driving task into a single pipeline that can be trained in an end-to-end fashion by passing latent representations between the different modules.…

Recent advancements in vision foundation models (VFMs) have revolutionized visual perception in 2D, yet their potential for 3D scene understanding, particularly in autonomous driving applications, remains underexplored. In this paper, we…