Related papers: UniHead: Unifying Multi-Perception for Detection H…

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different datasets. The training procedure uses homographic…

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various…

Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional…

Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted components, it is very difficult to reason about the…

We propose FusionBERT, a novel multi-view visual fusion framework for image-3D multimodal retrieval. Existing image-3D representation learning methods predominantly focus on feature alignment of a single object image and its 3D model,…

In the past few years, mobile deep-learning deployment progressed by leaps and bounds, but solutions still struggle to accommodate its severe and fluctuating operational restrictions, which include bandwidth, latency, computation, and…

We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach…

How do we build a general and broad object detection system? We use all labels of all concepts ever annotated. These labels span diverse datasets with potentially inconsistent taxonomies. In this paper, we present a simple method for…

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly…

Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era. Nevertheless, jointly conducting moment retrieval and highlight…

We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple…

Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic…

Real-world object detection is a challenging task where the captured images/videos often suffer from complex degradations due to various adverse weather conditions such as rain, fog, snow, low-light, etc. Despite extensive prior efforts,…

Advanced driver assistance systems require a comprehensive understanding of the driver's mental/physical state and traffic context but existing works often neglect the potential benefits of joint learning between these tasks. This paper…

Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two…

Transformer architecture has emerged to be successful in a number of natural language processing tasks. However, its applications to medical vision remain largely unexplored. In this study, we present UTNet, a simple yet powerful hybrid…

Conventional object detectors rely on cross-entropy classification, which can be vulnerable to class imbalance and label noise. We propose CLIP-Joint-Detect, a simple and detector-agnostic framework that integrates CLIP-style contrastive…

Radars, due to their robustness to adverse weather conditions and ability to measure object motions, have served in autonomous driving and intelligent agents for years. However, Radar-based perception suffers from its unintuitive sensing…

Cooperative perception allows connected vehicles and roadside infrastructure to share sensor observations, creating a fused scene representation beyond the capability of any single platform. However, most cooperative 3D object detectors use…