1386 papers
This paper introduces ENIGMA-360, a publicly released, temporally synchronized ego-exo dataset containing 360 annotated procedural videos from real industrial scenarios to advance human behavior understanding and establish baselines for tasks like action segmentation and interaction detection.
This paper introduces LAP, a novel procedure planning model that leverages a fine-tuned Vision Language Model to convert visual observations into distinctive text embeddings for a diffusion-based planner, achieving state-of-the-art performance on multiple benchmarks by effectively resolving visual ambiguities through language.
LogoDiffuser is a training-free method that leverages multimodal diffusion transformers and letter-aware attention control to generate high-quality, multilingual logo designs by inputting target characters as images to preserve structural integrity while applying creative styles.
This paper introduces PanoAffordanceNet, a novel framework and the first high-quality dataset (360-AGD) designed to enable holistic affordance grounding in 360-degree indoor environments by addressing challenges like geometric distortion and semantic dispersion through distortion-aware calibration and multi-level constraints.
The paper proposes "Ego," an efficient personalization method for vision-language models that extracts visual tokens representing target concepts via internal attention mechanisms to serve as memory, enabling strong performance across single-concept, multi-concept, and video personalization tasks without requiring additional training stages or external modules.
This paper challenges the assumption that neutralizing known triggers eliminates backdoors by demonstrating that perceptually distinct "alternative triggers" can reliably activate latent backdoor directions in feature space, thereby advocating for defenses that target these underlying representation patterns rather than specific input triggers.
This paper identifies that deep neural networks frequently encode the absence of concepts to drive neuron activation—a phenomenon largely overlooked by standard explainable AI methods—and proposes simple extensions to attribution and feature visualization techniques to effectively reveal and leverage these "missing" concepts for better model interpretation and debiasing.
This paper introduces Test-time Ego-Exo Adaptation for Action Anticipation (TEA), a novel task addressed by the Dual-Clue enhanced Prototype Growing Network (DCPGN) which utilizes a Multi-Label Prototype Growing Module and a Dual-Clue Consistency Module to effectively bridge the inter-view gap and adapt models online without target-view training data.
This paper introduces a new fine-grained Audio-Visual Learning task called Region-Aware Sound Source Understanding (RA-SSU), supported by two novel datasets (f-Music and f-Lifescene) and a state-of-the-art model named SSUFormer, which utilizes specialized modules to achieve precise sound source segmentation and detailed frame-level textual descriptions.
ConfCtrl is a confidence-aware video interpolation framework that enables precise camera control in video diffusion for novel view synthesis by combining confidence-weighted point cloud projections with a Kalman-inspired predict-update mechanism to balance pose guidance and geometric consistency while reconstructing unseen regions.
BrainSTR is a spatio-temporal contrastive learning framework that enhances the interpretability of dynamic brain network modeling for neuropsychiatric diagnosis by adaptively partitioning brain states, identifying critical phases, and extracting sparse, disease-specific connectivity patterns to construct a discriminative semantic space validated across ASD, BD, and MDD datasets.
This paper introduces VLM-Loc, a framework that leverages large vision-language models to achieve precise text-to-point-cloud localization by transforming 3D maps into bird's-eye-view images and scene graphs for enhanced spatial reasoning, alongside the release of the CityLoc benchmark for systematic evaluation.
This paper introduces MA-EgoQA, a novel benchmark and dataset featuring 1,700 questions across five categories designed to evaluate the ability of AI models to understand and reason over multiple long-horizon egocentric videos from embodied agents, alongside a proposed baseline model named EgoMAS that highlights current limitations in system-level multi-agent understanding.
CycleULM is a novel, label-free deep learning framework that leverages CycleGAN to bridge the simulation-to-reality gap in ultrasound localisation microscopy, significantly enhancing microbubble localisation accuracy, image resolution, and processing speed for real-time clinical application without requiring paired ground truth data.
This paper introduces MissBench, a benchmark and framework for multimodal affective computing that addresses the gap in evaluating models under realistic, imbalanced missing modality conditions by standardizing protocols and proposing new diagnostic metrics (MEI and MLI) to reveal hidden modality inequities and optimization imbalances.
The paper introduces InternVL-U, a lightweight 4B-parameter unified multimodal model that democratizes advanced understanding, reasoning, generation, and editing capabilities by employing a modular architecture and a reasoning-centric data synthesis pipeline, achieving superior performance-efficiency balance that outperforms significantly larger baselines like BAGEL.
The paper introduces DISPLAY, a framework for generating controllable and physically consistent human-object interaction videos by utilizing sparse motion guidance (wrist coordinates and object bounding boxes), an object-stressed attention mechanism, and a multi-task auxiliary training strategy to overcome limitations in flexibility, generalization, and data scarcity.
This paper introduces CourtSI, a large-scale dataset and benchmark for evaluating spatial intelligence in vision-language models within sports scenarios, revealing significant performance gaps in existing models while demonstrating that fine-tuning on this data substantially improves accuracy and generalization.
WikiCLIP is an efficient contrastive framework for open-domain visual entity recognition that leverages large language model embeddings enhanced by a Vision-Guided Knowledge Adaptor and Hard Negative Synthesis to significantly outperform generative baselines while reducing inference latency by nearly 100 times.
This paper identifies a structural gradient failure in Chamfer distance optimization that causes point cloud collapse, demonstrating that introducing non-local coupling mechanisms is a necessary condition to suppress this collapse and achieve successful 3D shape optimization.