4187 papers
This paper introduces PinCLIP, a large-scale foundational multimodal representation model for Pinterest that employs a novel hybrid Vision Transformer architecture and neighbor alignment objectives to overcome VLM integration challenges, resulting in significant improvements in multi-modal retrieval accuracy, cold-start content distribution, and overall user engagement.
This paper introduces PolyV, a unified large vision model that achieves cross-vision synergy across images, videos, and 3D data through a sparse Mixture-of-Experts architecture with dynamic routing and a synergy-aware training paradigm, resulting in significant performance improvements over existing models.
This paper proposes a novel confidence-aware monocular depth estimation framework for minimally invasive surgery that leverages calibrated confidence targets and a specialized loss function to improve depth accuracy and provide reliable per-pixel confidence maps, thereby addressing challenges posed by endoscopic image artifacts like smoke and blur.
This paper introduces L2G-Det, a novel framework that detects and segments specific object instances in open-world scenes by leveraging dense local patch matching to generate candidate points, which are then refined and used to prompt an augmented Segment Anything Model for robust mask reconstruction without relying on traditional object proposals.
This paper introduces Ambient Radio Sensing (ARS), a novel ISAC approach that repurposes ambient 5G signals for human activity detection via a passive self-mixing hardware architecture and a cross-modal learning framework, effectively overcoming spectrum scarcity while preserving privacy.
This paper proposes a VQA-inspired data augmentation framework that generates natural-language questions about character-level attributes to enhance scene and handwritten text recognition models, resulting in significant improvements in transcription accuracy on benchmark datasets.
This paper introduces a novel Traffic Scene Graph Generation framework that leverages accident data and depth cues to model safety-relevant relations between hazards and the ego vehicle, thereby enhancing situational awareness in complex driving scenarios.
This paper proposes DM-CFO, a diffusion model-based framework that integrates text and graph constraints for layout generation with collision-free optimization via 3D Gaussian updates and distance regularization to produce realistic, intersection-free compositional 3D tooth designs.
This paper proposes a framework that enhances penguin detection and identification in animal facilities by integrating motion cues into a modified YOLO11 detector for improved temporal consistency and employing tracklet-based contrastive learning to generate coherent feature embeddings for individual recognition.
This paper proposes a robust method for tracking feral horses in aerial video by employing oriented bounding boxes and a novel head-orientation estimation technique using multi-detector voting to resolve 180° flipping ambiguities, thereby achieving 99.3% accuracy in distinguishing head from tail for continuous trajectory analysis.
The paper proposes ParaHydra, a novel distributed multi-view image compression framework featuring an OmniParallax Attention Mechanism and a Parallax Multi Information Fusion Module that adaptively aligns and integrates inter-view correlations, enabling it to significantly outperform state-of-the-art multi-view codecs in both bitrate efficiency and computational speed.
This paper introduces LeafInst, a novel instance segmentation network designed for fine-grained forestry leaf analysis in open-field UAV imagery, and validates its superior performance on the newly constructed Poplar-leaf benchmark and the public PhenoBench dataset.
This paper introduces RAGTrack, a novel Retrieval-Augmented Generation framework that enhances RGB-Thermal tracking by integrating textual descriptions via Multi-modal Large Language Models and employing adaptive token fusion with context-aware reasoning to overcome appearance variations and modality gaps.
The paper introduces CoRe-BT, a multimodal benchmark comprising 310 patients with MRI, histopathology, and pathology reports, designed to evaluate robust brain tumor typing under realistic conditions of missing clinical data.
This paper presents a rigorous framework that extends neural operators to robustly handle out-of-distribution input functions by leveraging kernel approximations and Reproducing Kernel Hilbert Space theory to ensure accurate prediction of both function values and derivatives, validated through solutions of elliptic partial differential equations on manifolds.
This paper introduces Image-based Prompt Injection (IPI), a black-box attack that embeds adversarial instructions into natural images to hijack Multimodal Large Language Models, demonstrating a 64% success rate in manipulating model outputs while remaining visually imperceptible to humans.
The paper presents InfinityStory, a novel framework, dataset, and model that overcome key limitations in long-form video generation by ensuring background and character consistency across shots while enabling seamless multi-subject transitions for hour-long narratives.
The paper proposes SCFlowFR, a one-step face restoration method that leverages data-dependent coupling, conditional mean estimation, and a shortcut constraint to model low-to-high quality dependencies, thereby eliminating path crossovers and enabling high-quality, single-step inference.
This dissertation presents a comprehensive field imaging framework that leverages advanced computer vision algorithms, including 2D instance segmentation and an integrated 3D reconstruction-segmentation-completion approach, to overcome the limitations of traditional methods and enable accurate morphological characterization of construction aggregates across diverse field scenarios.
This paper introduces InEdit-Bench, the first benchmark designed to evaluate the ability of multimodal generative models to reason over intermediate logical pathways in complex image editing tasks, revealing significant shortcomings in current models' capacity for dynamic reasoning and causal understanding.