7560 papers
The paper introduces OmniFall, a unified multi-domain benchmark comprising 80 hours of harmonized staged, synthetic, and in-the-wild videos with dense frame-level annotations, designed to enable robust and privacy-preserving fall detection models that generalize effectively to uncontrolled real-world environments.
Cora is a novel few-step diffusion framework for image editing that leverages correspondence-aware noise correction and interpolated attention maps to effectively preserve structural attributes and identity while enabling significant non-rigid deformations, object modifications, and content generation with minimal artifacts.
This paper introduces ECAM, a contrastive learning-based module that integrates with existing trajectory forecasting models to significantly reduce environmental collision rates by better accounting for environmental context.
This paper proposes LLM-EMF, a novel cross-domain sequential recommendation framework that leverages frozen CLIP embeddings and a multiple attention mechanism to fuse visual and LLM-enhanced textual data, thereby significantly outperforming existing methods in modeling complex user preferences across diverse e-commerce domains.
This paper proposes Long-Tailed Knowledge Distillation (LTKD), a novel framework that decomposes the distillation objective into cross-group and within-group losses to calibrate a biased teacher's predictions and ensure balanced knowledge transfer, thereby significantly improving accuracy on long-tailed distributions.
This paper introduces DyME, a novel training paradigm that dynamically balances Supervised Fine-Tuning and Reinforcement Learning with Verifiable Reward, complemented by a synergistic Visual Supervision mechanism, to effectively empower Small Vision-Language Models with reliable thinking capabilities while overcoming the limitations of existing training methods.
The paper introduces SelvaBox, the largest open-access high-resolution drone imagery dataset for tropical tree crown detection, which enables the development of robust models that achieve state-of-the-art performance through both zero-shot generalization and unified multi-resolution training.
This paper proposes a concept-based adversarial attack framework that generates diverse, concept-preserving adversarial examples by operating on a probabilistic distribution of concepts rather than modifying single images, thereby achieving higher attack efficiency while maintaining the underlying identity or category.
This paper demonstrates how to develop a fully interpretable machine learning model for detecting overshooting tops in satellite imagery by using Explainable Boosting Machines combined with knowledge-guided feature extraction and human-in-the-loop refinement to prioritize transparency and domain expertise over peak accuracy.
The paper proposes pFedMMA, a personalized federated learning framework that utilizes multi-modal adapters with a globally shared projection to achieve state-of-the-art trade-offs between personalization and generalization for Vision-Language Models while maintaining communication efficiency.
This paper proposes new conformal prediction methods, including a prevalence-adjusted softmax score and an interpolation procedure, to effectively balance prediction set size and class-conditional coverage for long-tailed classification tasks where rare classes are often omitted.
This paper introduces BEAST, a scalable self-supervised framework that pretrains vision transformers using masked autoencoding and temporal contrastive learning to enable accurate behavioral analysis, pose estimation, and action segmentation across diverse species with minimal labeled data.
This paper presents a pipeline that utilizes a CNN-based primitive initializer to generate coarse 3D models and pose estimates from monocular images, which significantly accelerates and reduces the data requirements for training high-fidelity 3D Gaussian Splatting models of non-cooperative spacecraft even under noisy or implicit pose conditions.
DA-Occ is an efficient, direction-aware 2D convolution framework that enhances 3D occupancy prediction for autonomous driving by integrating height-score projection with depth-based lifting to preserve vertical geometry while achieving a strong balance between accuracy and real-time inference speed.
AutoDebias is an automated framework that leverages vision-language models and CLIP-guided training to detect and neutralize malicious backdoor attacks in text-to-image models, effectively mitigating injected biases while preserving image quality and diversity.
This paper introduces AMBER-AFNO, a lightweight 3D medical image segmentation benchmark that replaces computationally expensive self-attention mechanisms with Adaptive Fourier Neural Operators to achieve quasi-linear complexity and state-of-the-art performance on public datasets.
AnimateScene is a unified framework that enables camera-controllable 4D human animation in arbitrary 3D scenes by integrating automatic collision-free placement, training-free style alignment, and joint post-reconstruction for smooth, coherent dynamic videos.
This paper introduces a deep learning framework, BeeNet, which successfully reconstructs the geometric shapes of flowers from their electric fields generated by nearby charged arthropods, demonstrating that electroreception can provide rich spatial information for pollinators.
This paper proposes a structure-aware contrastive learning paradigm that leverages hard samples and specialized loss functions to significantly enhance vision-language models' ability to understand the structured, symbolic information inherent in diagrams, demonstrating superior performance on flowchart-based tasks compared to standard CLIP approaches.
The paper introduces Draw-In-Mind (DIM), a unified multimodal model that rebalances designer-painter roles by explicitly assigning design responsibilities to the understanding module through a specialized dataset of long-context pairs and chain-of-thought blueprints, achieving state-of-the-art image editing performance despite its compact parameter scale.