22 accepted papers
Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks. However, existing approaches often require leveraging external pretrained models, making it difficult to disentangle the effects of data selectio…
Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fi
End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong detection performance, these methods suffer from relatively low association accuracy. Through detailed analysis, we observe
Open-set 3D object retrieval (3DOR) is an emerging task aiming to retrieve 3D objects of unseen categories beyond the training set. Existing methods typically utilize all modalities (i.e., voxels, point clouds, multi-view images) and train specific backbones before fusion. However, they still strugg…
End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives and lacks of planning-oriented understanding, which limits th…
Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrates the generalizable knowledge embedded in FMs with the dynamic modeling capabilities of WMs to enable open-ended task s…
Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks. However, lacking well-defined attack objectives, existing jailbreak methods of…
This paper presents PlanarSplatting, an ultra-fast and accurate surface reconstruction approach for multi-view indoor images. We take the 3D planes as the main objective due to their compactness and structural expressiveness in indoor scenes, and develop an explicit optimization framework that learn…
In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when the agent maximizes the accumulated reward, it also fulfills
Generating immersive 360deg indoor panoramas from 2D top-down views has applications in virtual reality, interior design, real estate, and robotics. This task is challenging due to the lack of explicit 3D structure and the need for geometric consistency and photorealism. We propose Top2Pano, an end-…
3D plane reconstruction from a single image is a crucial yet challenging topic in 3D computer vision. Previous state-of-the-art (SOTA) methods have focused on training their system on a single dataset from either indoor or outdoor domain, limiting their generalizability across diverse testing data.…
In various applications, such as robotic navigation and remote visual assistance, expanding the field of view (FOV) of the camera proves beneficial for enhancing environmental perception. Unlike image outpainting techniques aimed solely at generating aesthetically pleasing visuals, these application…
Deep learning has been successfully used to automate the modeling process that trains a network/model from a given experimental dataset to calculate the output directly using high-dimensional complex raw data. However, the trained network is an inverse of the welding process (forward process) that p
The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, and occlusions. In this paper, we propose the Cascade Occluded Attention Transformer (COAT) for end-to-end person search.…
In aerial cooperative transportation missions, it has been recognized that for small-sized but heavy payloads, the cable-suspended framework is a preferred manner. However, to maintain proper safe flight distances, cables always stay inclined, which implies that horizontal force components have to b…
This letter illustrates how a challenging problem be solved by assuring the adequacy of the raw information and using an appropriate deep learning network to extract the relevant information. The problem concerned is accurate monitoring of the penetration, in a fully penetrated weld pool, as quantif
Word sense disambiguation (WSD), identifying the most suitable meaning of ambiguous words in the given contexts according to a predefined sense inventory, is one of the most classical and challenging tasks in natural language processing. Benefiting from the powerful ability of deep neural networks,…
Human trajectory prediction has received increased attention lately due to its importance in applications such as autonomous vehicles and indoor robots. However, most existing methods make predictions based on human-labeled trajectories and ignore the errors and noises in detection and tracking. In…
Nowadays, the prevalence of sensor networks has enabled tracking of the states of dynamic objects for a wide spectrum of applications from autonomous driving to environmental monitoring and urban planning. However, tracking realworld objects often faces two key challenges: First, due to the limitati…
This letter presents a virtual reality (VR) human–robot interaction welding system that allows human welders to manipulate a welding robot and undertake welding tasks naturally and intuitively via consumer-grade VR hardware (HTC Vive). In this system, human welders’ operations are captured by motion
Person re-identification (re-ID) is a highly challenging task due to large variations of pose, viewpoint, illumination, and occlusion. Deep metric learning provides a satisfactory solution to person re-ID by training a deep network under supervision of metric loss, e.g., triplet loss. However, the p…
In this paper we tackle the problem of capturing the dense, detailed 3D geometry of generic, complex non-rigid meshes using a single RGB-only commodity video camera and a direct approach. While robust and even real-time solutions exist to this problem if the observed scene is static, for non-rigid…