3893 papers
This paper proposes a deep ensemble learning framework that fuses four independent CNN-ViT hybrid models to overcome the performance bottlenecks of redundant feature representations, achieving state-of-the-art accuracy on remote sensing image classification datasets while maintaining computational efficiency.
Cog2Gen3D is a 3D cognition-guided diffusion framework that integrates semantic and absolute geometric features into a unified latent graph to overcome scale inconsistencies and achieve physically plausible, structurally rational 3D generation.
VS3R is a novel video stabilization framework that synergizes feed-forward 3D reconstruction with generative video diffusion to achieve robust, high-fidelity full-frame stabilization by jointly estimating camera parameters and depth while effectively restoring disoccluded regions.
The paper introduces MACRO, a self-evolving medical imaging agent that autonomously discovers and synthesizes reusable composite tools from verified execution trajectories to overcome the brittleness of static tool chains and enhance multi-step clinical decision-making across diverse domains.
This paper introduces TumorChain, a multimodal interleaved reasoning framework paired with the large-scale TumorCoT dataset, to enhance the traceability, accuracy, and reliability of clinical tumor analysis by integrating 3D CT imaging with step-by-step Chain-of-Thought reasoning for lesion characterization and pathology prediction.
The paper proposes PatchCue, a novel patch-based visual cue paradigm that enhances Vision-Language Model reasoning by aligning with human perceptual habits and leveraging patch-tokenized inputs through a two-stage training process, thereby outperforming existing pixel-level and point-based approaches across diverse benchmarks.
This paper introduces MemSeg-Agent, a memory-augmented framework that shifts adaptation from weight space to memory space to enable efficient few-shot learning, federated learning, and test-time adaptation for robust medical image segmentation without requiring model fine-tuning.
This paper presents a systematic evaluation demonstrating that while small synthetic novel view additions improve Video Place Recognition (VPR) performance, the effectiveness of larger additions depends more on the quantity of views and dataset imagery type than on the magnitude of the viewpoint change.
CylinderSplat is a feed-forward framework for panoramic 3D Gaussian Splatting that introduces a novel cylindrical Triplane representation and a dual-branch architecture to effectively handle occlusions and geometric distortions in $360^\circ$ scenes, achieving state-of-the-art results in both single-view and multi-view novel view synthesis.
PixARMesh is a novel autoregressive method that directly reconstructs complete, high-fidelity, and artist-ready 3D indoor scene meshes from a single RGB image by jointly predicting object layout and geometry within a unified model, eliminating the need for implicit fields or post-hoc optimization.
The paper proposes InnoAds-Composer, a single-stage framework that efficiently generates e-commerce posters by integrating subject, text, and style controls through an optimized token routing mechanism and a text enhancement module, while also introducing a new high-quality dataset and benchmark for this task.
This paper proposes three bias mitigation techniques—top-k concept filtering, removal of biased concepts, and adversarial debiasing—to address information leakage in Concept Bottleneck Models, thereby achieving superior fairness-performance tradeoffs for interpretable image classification compared to prior work.
CollabOD is a lightweight collaborative detection framework designed to enhance UAV small object detection by integrating structural detail preservation, cross-path feature alignment, and localization-aware lightweight strategies to overcome challenges like scale variation and feature degradation in high-altitude imagery.
This paper introduces Art3D, a novel framework that shifts 2D-to-3D conversion from geometric accuracy to artistic coherence by synthesizing disparities that capture professional cinematic intent through a dual-path architecture and indirect supervision.
Pano3DComposer is an efficient feed-forward framework that generates high-fidelity, complete 360-degree 3D scenes from single panoramic images by decoupling object generation from layout estimation through a novel plug-and-play Object-World Transformation Predictor and a Coarse-to-Fine alignment mechanism.
This paper introduces CORE-Seg, a reinforcement learning-driven framework that integrates a Semantic-Guided Prompt Adapter with a progressive SFT-to-GRPO training strategy to bridge the gap between visual segmentation and cognitive reasoning for complex medical lesions, achieving state-of-the-art performance on the newly proposed ComLesion-14K Chain-of-Thought benchmark.
This paper introduces BlackMirror, a novel black-box, training-free framework that detects backdoored text-to-image models by identifying and verifying the stability of partial semantic deviations between instructions and generated images, overcoming the limitations of existing image-similarity-based methods against diverse backdoor attacks.
The paper introduces RAC (Rectified Flow Auto Coder), a novel architecture that replaces traditional VAEs by leveraging rectified flow for multi-step, bidirectional inference, thereby achieving superior reconstruction and generation quality with significantly reduced parameters and computational cost.
This paper introduces RAID, a large-scale dataset for driver risk perception research, and proposes a weakly-supervised framework that leverages driver maneuvers and responses to identify risk sources, achieving significant performance improvements over state-of-the-art methods.
This paper introduces TAR-ViTPose, a novel video-based human pose estimation method that enhances static Vision Transformers by employing joint-centric temporal aggregation and global restoring attention to leverage temporal coherence, thereby achieving superior accuracy and efficiency compared to existing state-of-the-art approaches.