3290 papers
This paper introduces CountOCC, a novel amodal counting framework that overcomes the limitations of existing methods under occlusion by hierarchically reconstructing complete object features through multimodal guidance and visual equivalence objectives, achieving state-of-the-art performance on newly established occlusion-augmented benchmarks.
This paper introduces the Angular Gradient Sign Method, a novel adversarial attack for hyperbolic networks that leverages the geometric decomposition of gradients to apply perturbations solely along angular (semantic) directions, thereby achieving higher fooling rates and revealing unique vulnerabilities in hierarchical embeddings compared to conventional Euclidean-based methods.
The paper proposes Video2Layout, a two-stage framework that reconstructs metric-grounded spatial layouts using continuous object boundary coordinates instead of discretized grids, thereby enhancing fine-grained spatial reasoning in Multimodal Large Language Models and achieving superior performance on spatial benchmarks.
This paper proposes the Multi-Order Matching Network (MOMNet), an alignment-free framework that achieves state-of-the-art depth super-resolution by adaptively retrieving and integrating misaligned RGB information through a novel multi-order matching and aggregation mechanism.
This paper introduces DualMindVLM, a visual language model that leverages a dual-mode thinking mechanism to dynamically select between fast, intuitive responses and slow, deliberate reasoning based on problem complexity, thereby achieving state-of-the-art performance with significantly improved token efficiency.
The paper proposes the Radiative-Structured Neural Operator (RSNO), a novel deep learning framework that reconstructs hyperspectral images from multispectral observations by learning continuous spectral mappings under radiative priors and employing angular-consistent projection to ensure physical consistency and eliminate color distortion.
The paper proposes UnfoldLDM, a deep unfolding framework that integrates a multi-granularity degradation-aware module for robust degradation estimation and a degradation-resistant latent diffusion model with an over-smoothing correction transformer to effectively address blind image restoration by overcoming degradation-specific dependencies and suppressing over-smoothing bias.
This paper presents a stable, real-time multi-drone GNSS tracking system for marine robots that integrates visual detection, multi-object tracking, triangulation, and a confidence-weighted Extended Kalman Filter with cross-drone ID alignment to overcome the limitations of underwater signal loss and traditional alternatives.
This paper introduces Yo'City, an agentic framework that leverages large models for hierarchical planning and a self-critic expansion loop to generate personalized, boundless, and spatially coherent 3D realistic city scenes, outperforming existing state-of-the-art methods across multiple evaluation metrics.
This paper proposes "Shortcut Invariance," a targeted Jacobian regularization method that improves out-of-distribution generalization by injecting anisotropic noise into a disentangled latent space to flatten decision boundaries along shortcut-aligned axes, thereby eliminating the need for explicit shortcut labels or conflicting training samples.
This study introduces ForamDeepSlice, a high-accuracy deep learning framework that combines an ensemble of ConvNeXt-Large and EfficientNetV2-Small models with a rigorous specimen-level split dataset to achieve 95.64% accuracy in classifying foraminifera species from 2D micro-CT slices, while also providing an interactive dashboard for real-time identification and 3D matching.
The paper proposes S2AM3D, a novel framework that integrates 2D segmentation priors with 3D consistent supervision and a scale-aware prompt decoder to achieve robust, generalizable, and real-time controllable part segmentation for 3D point clouds, supported by a newly introduced large-scale dataset.
HiconAgent introduces History Context-aware Policy Optimization (HCPO), featuring Dynamic Context Sampling and Anchor-guided History Compression, to enable a compact 3B-parameter GUI agent to outperform larger models in navigation accuracy while significantly reducing computational costs.
MAViD is a novel multimodal framework that employs a Conductor-Creator architecture, combining autoregressive audio and diffusion-based video generation with a specialized fusion module, to overcome existing limitations and achieve seamless, long-duration, and contextually coherent audio-visual dialogue understanding and generation.
This paper reveals that visual token information in Vision Large Language Models progressively vanishes at a depth-dependent "information horizon," beyond which existing pruning methods underperform random selection, leading to a novel strategy that integrates random pruning to achieve state-of-the-art efficiency without sacrificing accuracy.
This paper addresses the challenges of off-road road network extraction by introducing the WildRoad dataset and MaGRoad, a novel path-centric framework that overcomes the limitations of existing node-centric models to achieve state-of-the-art performance and faster inference in wild terrains.
This paper presents a two-step generative data augmentation framework combining rule-based mask warping and unpaired image-to-image translation to address the scarcity of masked face datasets, achieving performance improvements with minimal training data while explicitly noting its origins as a resource-constrained coursework project that lacked downstream quantitative evaluation.
The paper introduces SALVE, a unified framework that combines sparse autoencoders and feature-level saliency mapping to discover, validate, and precisely edit neural network weights, enabling interpretable and robust control over both convolutional and transformer-based models.
The paper introduces ReMeDI-SAM3, a training-free extension of SAM3 that enhances surgical instrument segmentation in endoscopy by implementing relevance-aware memory filtering, piecewise interpolation, and feature-based re-identification to overcome challenges like occlusions and rapid motion, achieving significant zero-shot performance improvements over existing methods.
This study analyzes the discrepancies between objective and subjective urban greenery perceptions across five countries using street view imagery and a survey of 1,000 participants, revealing that while demographics and personality have little influence, an individual's geographic location is a primary factor shaping how they perceive green spaces.