29 accepted papers
Embodied World Models (EWMs) have emerged as a scalable and risk-free paradigm for evaluating Vision-Language-Action (VLA) systems. However, their reliability as evaluation benchmarks is often limited by the representation gap between low-dimensional actions and high-dimensional video synthesis. Thi…
Document image dewarping remains a challenging task in the deep learning era. While existing methods have improved by leveraging text line awareness, they typically focus only on a single horizontal dimension. In this paper, we propose a fine-grained deformation perception model that focuses on Dual
Self-supervised monocular depth estimation serves as a key task in the development of endoscopic navigation systems. However, performance degradation persists due to uneven illumination inherent in endoscopic images, particularly in low-intensity regions. Existing low-light enhancement techniques fa
Restoring degraded document image is essential for both improving visual quality and optimizing performance in downstream document analysis tasks. Although existing methods have demonstrated substantial improvements in restoration outcomes, they primarily address single-type degradation scenarios. C
Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich in fine-grained detail. Although recent approaches can produce complex and natural movements, they usually operate at only one temporal scale, which
Verification is a key bottleneck in improving inference speed while maintaining distribution fidelity in Speculative Decoding. Recent work has shown that sequence-level verification leads to a higher number of accepted tokens compared to token-wise verification. However, existing solutions often rel…
We present VisAssist, the first large-scale video question-answering dataset with 13,413 real-world videos captured by visually impaired users, addressing a critical gap in assistive vision research. Unlike existing benchmarks relying on third-person footage, VisAssist provides authentic first-perso
Decoupling domain-variant information (DVI) from domain-invariant information (DII) serves as a prominent strategy for mitigating domain shifts in the practical implementation of deep learning algorithms. However, in medical settings, concerns surrounding data collection and privacy often restrict a…
Sleep apnea is a common sleep disorder that, if untreated, can lead to serious health issues. Snoring is a typical symptom of sleep apnea and can be utilized to develop a noncontact automatic detection method for sleep apnea severity classification (SASC). However, due to patient heterogeneity, the…
Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical issues with LS. First, LS induces overconfidence in misclassified samples. Second, it compacts feature representations…
Accurate and realistic 3D scene reconstruction enables the lifelike creation of autonomous driving simulation environments. With advancements in 3D Gaussian Splatting (3DGS), previous studies have applied it to reconstruct complex dynamic driving scenes. These methods typically require expensive LiD
Training deep learning models for semantic occupancy prediction is challenging due to factors such as a large number of occupancy cells, severe occlusion, limited visual cues, complicated driving scenarios, etc. Recent methods often adopt transformer-based architectures given their strong capability…
PanTS is a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis. It contains 36,390 CT scans from 145 medical centers, with expert-validated, voxel-wise annotations of over 993,000 anatomical structures, covering pancreatic tumors, pancreas head, body, and t…
Large language models (LLMs) have demonstrated remarkable capabilities in various domains, including radiology report generation. Previous approaches have attempted to utilize multimodal LLMs for this task, enhancing their performance through the integration of domain-specific knowledge retrieval. H…
Learning visuomotor policy from human demonstrations serves as an effective method for robots to acquire complex tasks. However, data collection on mobile platforms such as drones is extremely challenging, resulting in most research being conducted with robots in stationary conditions for data colle…
We present SeePhys, a large-scale multimodal benchmark for LLM reasoning grounded in physics questions ranging from middle school to PhD qualifying exams. The benchmark covers 7 fundamental domains spanning the physics discipline, incorporating 21 categories of highly heterogeneous diagrams. In cont…
Object pose estimation, crucial in computer vision and robotics applications, faces challenges with the diversity of unseen categories. We propose a zero-shot method to achieve category-level 6-DOF object pose estimation, which exploits both 2D and 3D universal features of input RGB-D image to estab…
Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack methods make unrealistic assumptions, assuming that all trainin…
Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. However, current VLN frameworks often rely on static environments and optimal expert supervision, limiting their real-world applicability. To address this, we introduce Human-Aware Vision-…
Visual Odometry (VO) plays a pivotal role in autonomous systems, with a principal challenge being the lack of depth information in camera images. This paper introduces OCC-VO, a novel framework that capitalizes on recent advances in deep learning to transform 2D camera images into 3D semantic occupa…
The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfit to the table style in training set, and suffer from significant performance degradation when encountering out-of-distr…
There is an emerging trend of using neural implicit functions for map representation in Simultaneous Localization and Mapping (SLAM). Some pioneer works have achieved encouraging results on RGB-D SLAM. In this paper, we present a dense RGB SLAM method with neural implicit map representation. To reac…
This paper aims at the distorted document image rectification problem, the objective to eliminate the geometric distortion in the document images and realize document intelligence. Improving the readability of distorted documents is crucial to effectively extract information from deformed images. Ac…
Monocular scene reconstruction from posed images is challenging due to the complexity of a large environment. Recent volumetric methods learn to directly predict the TSDF volume and have demonstrated promising results in this task. However, most methods focus on how to extract and fuse the 2D featur…
In denoising and de-reverberation tasks, the dominant methods are complex spectral masking and complex spectral mapping. To combine advantages and improve speech enhancement performance, we propose a two-stage UNet (TSUNet) to estimate complex spectral masking and complex spectral mapping. We use a…
In recent years, deep learning-based approaches have significantly improved the performance of single-channel speech enhancement. However, due to the limitation of training data and computational complexity, real-time enhancement of full-band (48 kHz) speech signals is still very challenging. Becaus…
This paper proposes a deep recurrent Rotation Averaging Graph Optimizer (RAGO) for Multiple Rotation Averaging (MRA). Conventional optimization-based methods usually fail to produce accurate results due to corrupted and noisy relative measurements. Recent learning-based approaches regard MRA as a re…
In the ``Big Data'' age, the amount and distribution of data have increased wildly and changed over time in various time-series-based tasks, e.g weather prediction, network intrusion detection. However, deep learning models may become outdated facing variable input data distribution, which is called…
This paper presents an end-to-end neural network for multiple rotation averaging in SfM. Due to the manifold constraint of rotations, conventional methods usually take two separate steps involving spanning tree based initialization and iterative nonlinear optimization respectively. These methods can…