Related papers: Interactive Masked Image Modeling for Multimodal O…
Effective tracking of surrounding traffic participants allows for an accurate state estimation as a necessary ingredient for prediction of future behavior and therefore adequate planning of the ego vehicle trajectory. One approach for…
Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects, which plays a curtail role in high-level semantic understanding tasks. However, most works pursue designing better architectures to…
With the rapid progression of deep learning technologies, multi-modality image fusion has become increasingly prevalent in object detection tasks. Despite its popularity, the inherent disparities in how different sources depict scene…
Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure…
We present an imaging technique that allows the recovery of the transparency profile of wavelength-scale objects with deep subwavelength resolution based on far-field intensity measurements. The approach, interscale mixing microscopy (IMM),…
Multi-Object Tracking (MOT) has been a long-standing challenge in video understanding. A natural and intuitive approach is to split this task into two parts: object detection and association. Most mainstream methods employ meticulously…
We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text…
Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in 3D data, where…
LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…
Moving object segmentation plays a crucial role in understanding dynamic scenes involving multiple moving objects, while the difficulties lie in taking into account both spatial texture structures and temporal motion cues. Existing methods…
We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual…
Human action recognition is a crucial task for intelligent robotics, particularly within the context of human-robot collaboration research. In self-supervised skeleton-based action recognition, the mask-based reconstruction paradigm learns…
The practical problem of tracking a maneuvering aircraft during flight has always been a crucial task in order to safeguard airborne assets from unknown threats. Therefore, the need for an efficient target detection and identification…
Moving object detection (MOD) in remote sensing is significantly challenged by low resolution, extremely small object sizes, and complex noise interference. Current deep learning-based MOD methods rely on probability density estimation,…
Self-supervised learning through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) image representation learning, and thus embodies a significant potential for content-based image retrieval (CBIR)…
Recent image matting studies are developing towards proposing trimap-free or interactive methods for complete complex image matting tasks. Although avoiding the extensive labors of trimap annotation, existing methods still suffer from two…
Vision sensors are becoming more important in Intelligent Transportation Systems (ITS) for traffic monitoring, management, and optimization as the number of network cameras continues to rise. However, manual object tracking and matching…
What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale…
Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…
Camouflaged Object Detection (COD) stands as a significant challenge in computer vision, dedicated to identifying and segmenting objects visually highly integrated with their backgrounds. Current mainstream methods have made progress in…