Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2608.30844v1 Announce Type: cross Abstract: Interactive lesion segmentation in whole-body PET/CT requires a model to provide a strong initial prediction while also responding efficiently to spa...
arXiv:2505.16157v3 Announce Type: replace Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Tran...
arXiv:2509.06422v2 Announce Type: replace Abstract: Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods...
arXiv:2608.30521v1 Announce Type: new Abstract: Conventional algebraic triangulation solves 3D human pose estimation (HPE) from multi-view 2D keypoints. The typical approach, decoding 2D keypoints fr...
arXiv:2608.31073v1 Announce Type: new Abstract: Whole-heart segmentation (WHS) in computed tomography (CT) and magnetic resonance imaging (MRI) is affected by acquisition shifts and heterogeneous car...
arXiv:2608.30618v1 Announce Type: new Abstract: Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the trainin...
arXiv:2608.28681v1 Announce Type: new Abstract: Probability calibration aligns model confidence with predictive accuracy, enabling clinicians to identify unreliable segmentation regions. This alignme...
arXiv:2405.07392v4 Announce Type: replace-cross Abstract: Many existing visual SLAM methods can achieve high localization accuracy in dynamic environments by leveraging deep learning to mask moving o...
arXiv:2608.29315v1 Announce Type: cross Abstract: This work introduces Semantically-Guided Exploration (SGE), a modular exploration framework for ground vehicles that integrates pixel-level semantic...
arXiv:2608.28706v1 Announce Type: new Abstract: ViT detectors fix a uniform token grid before any learned stage. A native-resolution aerial detector must then choose between resolving few-pixel objec...
arXiv:2608.30621v1 Announce Type: cross Abstract: Collecting natural-language referring expressions along with region annotations, such as masks or boxes, is a major bottleneck in visual grounding (V...
arXiv:2608.29183v1 Announce Type: new Abstract: Conditional flow matching has enabled a step forward in object 6D pose estimation, achieving state-of-the-art performance by progressively denoising an...
arXiv:2608.29145v1 Announce Type: cross Abstract: The rapid expansion of low Earth orbit satellites such as Starlink is increasingly contaminating astronomical surveys. In practice, contaminated imag...
arXiv:2608.30633v1 Announce Type: cross Abstract: Timely post-disaster building damage assessment from satellite imagery is a critical engineering decision support task, yet it remains constrained by...
ClearText-Video (CTVid) is a large-scale, scene-text-aware benchmark that examines text-centric video understanding under varying quality conditions. It comprises 4,639 real-world egocentric videos, over 550,000 frames, 1.6 million human-verified scene-text annotations, and more than 220,000 spatial/temporal question–answer pairs in Chinese and English. For each high-quality video, CTVid provides matched degraded- and restored-quality variants, enabling studies of Text-Centric Video Restoration and Multi-Quality VideoQA, and revealing that visual enhancement does not always improve textual fidelity or downstream reasoning.
arXiv:2603.11521v2 Announce Type: replace-cross Abstract: Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and t...
arXiv:2608.28794v1 Announce Type: cross Abstract: Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs...
arXiv:2608.28699v1 Announce Type: new Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine...
arXiv:2608.30616v1 Announce Type: new Abstract: Pottery is a primary source for reconstructing the chronological and economic dimensions of past societies. Archaeologists often document ceramic finds...
arXiv:2608.30404v1 Announce Type: cross Abstract: Accurate segmentation of the coronary vessel lumen is a prerequisite for quantitative assessment of atherosclerotic plaque and perivascular adipose t...