arXiv subjects

Haoyu Chen

Publications and source records attributed to Haoyu Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

EventRR: Event Referential Reasoning for Referring Video Object Segmentation

Referring Video Object Segmentation (RVOS) aims to segment out the object in a video referred by an expression. Current RVOS methods view referring expressions as unstructured sequences, neglecting their crucial semantic structure essential for referent reasoning. Besides, in contrast to image-referring expressions whose semantics focus only on object attributes and object-object relations, video-referring expressions also encompass event attributes and event-event temporal relations. This complexity challenges traditional structured reasoning image approaches. In this paper, we propose the Event Referential Reasoning (EventRR) framework. EventRR decouples RVOS into object summarization part and referent reasoning part. The summarization phase begins by summarizing each frame into a set of bottleneck tokens, which are then efficiently aggregated in the video-level summarization step to exchange the global cross-modal temporal context. For reasoning part, EventRR extracts semantic eventful structure of a video-referring expression into highly expressive Referential Event Graph (REG), which is a single-rooted directed acyclic graph. Guided by topological traversal of REG, we propose Temporal Concept-Role Reasoning (TCRR) to accumulate the referring score of each temporal query from REG leaf nodes to root node. Each reasoning step can be interpreted as a question-answer pair derived from the concept-role relations in REG. Extensive experiments across four widely recognized benchmark datasets, show that EventRR quantitatively and qualitatively outperforms state-of-the-art RVOS methods. Code is available at https://github.com/bio-mlhui/EventRR

cs.CV↗

arXiv2025

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning

Vision-Language Models (VLMs) have achieved remarkable breakthroughs in recent years, enabling a diverse array of applications in everyday life. However, the substantial computational and storage demands of VLMs pose significant challenges for their efficient deployment on mobile devices, which represent the most ubiquitous and accessible computing platforms today. In this work, we introduce MagicVL-2B, a novel VLM meticulously optimized for flagship smartphones. MagicVL-2B leverages a lightweight visual encoder with fewer than 100M parameters and features a redesigned dynamic resolution scheme that adaptively generates image tokens without excessive modification of image dimensions. To further enhance the performance of this compact encoder within VLMs, we propose a multimodal curriculum learning strategy that incrementally increases task difficulty and data information density throughout training. This approach substantially improves the model's performance across a variety of sub-tasks. Extensive evaluations on standard VLM benchmarks demonstrate that MagicVL-2B matches the accuracy of current state-of-the-art models while reducing on-device power consumption by 41.1%. These results establish MagicVL-2B as a practical and robust solution for real-world mobile vision-language applications, enabling advanced multimodal intelligence to run directly on smartphones.

cs.CV↗

arXiv2025

MASIV: Toward Material-Agnostic System Identification from Videos

System identification from videos aims to recover object geometry and governing physical laws. Existing methods integrate differentiable rendering with simulation but rely on predefined material priors, limiting their ability to handle unknown ones. We introduce MASIV, the first vision-based framework for material-agnostic system identification. Unlike existing approaches that depend on hand-crafted constitutive laws, MASIV employs learnable neural constitutive models, inferring object dynamics without assuming a scene-specific material prior. However, the absence of full particle state information imposes unique challenges, leading to unstable optimization and physically implausible behaviors. To address this, we introduce dense geometric guidance by reconstructing continuum particle trajectories, providing temporally rich motion constraints beyond sparse visual cues. Comprehensive experiments show that MASIV achieves state-of-the-art performance in geometric accuracy, rendering quality, and generalization ability.

cs.CV↗

arXiv2025

New Measurements of the Deuteron to Proton F2 Structure Function Ratio

Nucleon structure functions, as measured in lepton-nucleon scattering, have historically provided a critical observable in the study of partonic dynamics within the nucleon. However, at very large parton momenta it is both experimentally and theoretically challenging to extract parton distributions due to the probable onset of non-perturbative contributions and the unavailability of high precision data at critical kinematics. Extraction of the neutron structure and the d-quark distribution have been further challenging due to the necessity of applying nuclear corrections when utilizing scattering data from a deuteron target to extract free neutron structure. However, a program of experiments has been carried out recently at the energy-upgraded Jefferson Lab electron accelerator aimed at significantly reducing the nuclear correction uncertainties on the d-quark distribution function at large partonic momentum. This allows leveraging the vast body of deuterium data covering a large kinematic range to be utilized for d-quark parton distribution function extraction. We present new data from experiment E12-10-002 carried out in Jefferson Lab Hall C on the deuteron to proton cross-section ratio at large BJorken-x. These results significantly improve the precision of existing data, and provide a first look at the expected impact on quark distributions extracted from global parton distribution function fits.

hep-ex↗

arXiv2025

Learning Transferable Facial Emotion Representations from Large-Scale Semantically Rich Captions

Current facial emotion recognition systems are predominately trained to predict a fixed set of predefined categories or abstract dimensional values. This constrained form of supervision hinders generalization and applicability, as it reduces the rich and nuanced spectrum of emotions into oversimplified labels or scales. In contrast, natural language provides a more flexible, expressive, and interpretable way to represent emotions, offering a much broader source of supervision. Yet, leveraging semantically rich natural language captions as supervisory signals for facial emotion representation learning remains relatively underexplored, primarily due to two key challenges: 1) the lack of large-scale caption datasets with rich emotional semantics, and 2) the absence of effective frameworks tailored to harness such rich supervision. To this end, we introduce EmoCap100K, a large-scale facial emotion caption dataset comprising over 100,000 samples, featuring rich and structured semantic descriptions that capture both global affective states and fine-grained local facial behaviors. Building upon this dataset, we further propose EmoCapCLIP, which incorporates a joint global-local contrastive learning framework enhanced by a cross-modal guided positive mining module. This design facilitates the comprehensive exploitation of multi-level caption information while accommodating semantic similarities between closely related expressions. Extensive evaluations on over 20 benchmarks covering five tasks demonstrate the superior performance of our method, highlighting the promise of learning facial emotion representations from large-scale semantically rich captions. The code and data will be available at https://github.com/sunlicai/EmoCapCLIP.

cs.CV↗

arXiv2025

SWIFT: A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening

Pansharpening aims to fuse high-resolution panchromatic (PAN) images with low-resolution multispectral (LRMS) images to generate high-resolution multispectral (HRMS) images. Although deep learning-based methods have achieved promising performance, they generally suffer from severe performance degradation when applied to data from unseen sensors. Adapting these models through full-scale retraining or designing more complex architectures is often prohibitively expensive and impractical for real-world deployment. To address this critical challenge, we propose a fast and general-purpose framework for cross-sensor adaptation, SWIFT (Sensitive Weight Identification for Fast Transfer). Specifically, SWIFT employs an unsupervised sampling strategy based on data manifold structures to balance sample selection while mitigating the bias of traditional Farthest Point Sampling, efficiently selecting only 3\% of the most informative samples from the target domain. This subset is then used to probe a source-domain pre-trained model by analyzing the gradient behavior of its parameters, allowing for the quick identification and subsequent update of only the weight subset most sensitive to the domain shift. As a plug-and-play framework, SWIFT can be applied to various existing pansharpening models. Extensive experiments demonstrate that SWIFT reduces the adaptation time from hours to approximately one minute on a single NVIDIA RTX 4090 GPU. The adapted models not only substantially outperform direct-transfer baselines but also achieve performance competitive with, and in some cases superior to, full retraining, establishing a new state-of-the-art on cross-sensor pansharpening tasks for the WorldView-2 and QuickBird datasets.

cs.CV↗

arXiv2025

Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation

Recent studies in speech-driven talking face generation achieve promising results, but their reliance on fixed-driven speech limits further applications (e.g., face-voice mismatch). Thus, we extend the task to a more challenging setting: given a face image and text to speak, generating both talking face animation and its corresponding speeches. Accordingly, we propose a novel framework, Face2VoiceSync, with several novel contributions: 1) Voice-Face Alignment, ensuring generated voices match facial appearance; 2) Diversity \& Manipulation, enabling generated voice control over paralinguistic features space; 3) Efficient Training, using a lightweight VAE to bridge visual and audio large-pretrained models, with significantly fewer trainable parameters than existing methods; 4) New Evaluation Metric, fairly assessing the diversity and identity consistency. Experiments show Face2VoiceSync achieves both visual and audio state-of-the-art performances on a single 40GB GPU.

cs.SD↗

arXiv2025

Hybrid-supervised Hypergraph-enhanced Transformer for Micro-gesture Based Emotion Recognition

Micro-gestures are unconsciously performed body gestures that can convey the emotion states of humans and start to attract more research attention in the fields of human behavior understanding and affective computing as an emerging topic. However, the modeling of human emotion based on micro-gestures has not been explored sufficiently. In this work, we propose to recognize the emotion states based on the micro-gestures by reconstructing the behavior patterns with a hypergraph-enhanced Transformer in a hybrid-supervised framework. In the framework, hypergraph Transformer based encoder and decoder are separately designed by stacking the hypergraph-enhanced self-attention and multiscale temporal convolution modules. Especially, to better capture the subtle motion of micro-gestures, we construct a decoder with additional upsampling operations for a reconstruction task in a self-supervised learning manner. We further propose a hypergraph-enhanced self-attention module where the hyperedges between skeleton joints are gradually updated to present the relationships of body joints for modeling the subtle local motion. Lastly, for exploiting the relationship between the emotion states and local motion of micro-gestures, an emotion recognition head from the output of encoder is designed with a shallow architecture and learned in a supervised way. The end-to-end framework is jointly trained in a one-stage way by comprehensively utilizing self-reconstruction and supervision information. The proposed method is evaluated on two publicly available datasets, namely iMiGUE and SMG, and achieves the best performance under multiple metrics, which is superior to the existing methods.

cs.CV↗

arXiv2025

Robust Multi-Manifold Clustering via Simplex Paths

This article introduces a novel, geometric approach for multi-manifold clustering (MMC), i.e. for clustering a collection of potentially intersecting, d-dimensional manifolds into the individual manifold components. We first compute a locality graph on d-simplices, using the dihedral angle in between adjacent simplices as the graph weights, and then compute infinity path distances in this simplex graph. This procedure gives a metric on simplices which we refer to as the largest angle path distance (LAPD). We analyze the properties of LAPD under random sampling, and prove that with an appropriate denoising procedure, this metric separates the manifold components with high probability. We validate the proposed methodology with extensive numerical experiments on both synthetic and real-world data sets. These experiments demonstrate that the method is robust to noise, curvature, and small intersection angle, and generally out-performs other MMC algorithms. In addition, we provide a highly scalable implementation of the proposed algorithm, which leverages approximation schemes for infinity path distance to achieve quasi-linear computational complexity.

stat.ML↗

arXiv2025

Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest

Industrial recommendation systems are typically composed of multiple stages, including retrieval, ranking, and blending. The retrieval stage plays a critical role in generating a high-recall set of candidate items that covers a wide range of diverse user interests. Effectively covering the diverse and long-tail user interests within this stage poses a significant challenge: traditional two-tower models struggle in this regard due to limited user-item feature interaction and often bias towards top use cases. To address these issues, we propose a novel multi-embedding retrieval framework designed to enhance user interest representation by generating multiple user embeddings conditioned on both implicit and explicit user interests. Implicit interests are captured from user history through a Differentiable Clustering Module (DCM), whereas explicit interests, such as topics that the user has followed, are modeled via Conditional Retrieval (CR). These methodologies represent a form of conditioned user representation learning that involves condition representation construction and associating the target item with the relevant conditions. Synergizing implicit and explicit user interests serves as a complementary approach to achieve more effective and comprehensive candidate retrieval as they benefit on different user segments and extract conditions from different but supplementary sources. Extensive experiments and A/B testing reveal significant improvements in user engagements and feed diversity metrics. Our proposed framework has been successfully deployed on Pinterest home feed.

cs.IR↗

arXiv2025

JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

Photo retouching has become integral to contemporary visual storytelling, enabling users to capture aesthetics and express creativity. While professional tools such as Adobe Lightroom offer powerful capabilities, they demand substantial expertise and manual effort. In contrast, existing AI-based solutions provide automation but often suffer from limited adjustability and poor generalization, failing to meet diverse and personalized editing needs. To bridge this gap, we introduce JarvisArt, a multi-modal large language model (MLLM)-driven agent that understands user intent, mimics the reasoning process of professional artists, and intelligently coordinates over 200 retouching tools within Lightroom. JarvisArt undergoes a two-stage training process: an initial Chain-of-Thought supervised fine-tuning to establish basic reasoning and tool-use skills, followed by Group Relative Policy Optimization for Retouching (GRPO-R) to further enhance its decision-making and tool proficiency. We also propose the Agent-to-Lightroom Protocol to facilitate seamless integration with Lightroom. To evaluate performance, we develop MMArt-Bench, a novel benchmark constructed from real-world user edits. JarvisArt demonstrates user-friendly interaction, superior generalization, and fine-grained control over both global and local adjustments, paving a new avenue for intelligent photo retouching. Notably, it outperforms GPT-4o with a 60% improvement in average pixel-level metrics on MMArt-Bench for content fidelity, while maintaining comparable instruction-following capabilities. Project Page: https://jarvisart.vercel.app/.

cs.CV↗

arXiv2025

PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony. To address this, we propose PosterCraft, a unified framework that abandons prior modular pipelines and rigid, predefined layouts, allowing the model to freely explore coherent, visually compelling compositions. PosterCraft employs a carefully designed, cascaded workflow to optimize the generation of high-aesthetic posters: (i) large-scale text-rendering optimization on our newly introduced Text-Render-2M dataset; (ii) region-aware supervised fine-tuning on HQ-Poster100K; (iii) aesthetic-text-reinforcement learning via best-of-n preference optimization; and (iv) joint vision-language feedback refinement. Each stage is supported by a fully automated data-construction pipeline tailored to its specific needs, enabling robust training without complex architectural modifications. Evaluated on multiple experiments, PosterCraft significantly outperforms open-source baselines in rendering accuracy, layout coherence, and overall visual appeal-approaching the quality of SOTA commercial systems. Our code, models, and datasets can be found in the Project page: https://ephemeral182.github.io/PosterCraft

cs.CV↗

arXiv2025

OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning

Representation learning, a task of learning latent vectors to represent entities, is a key task in improving search and recommender systems in web applications. Various representation learning methods have been developed, including graph-based approaches for relationships among entities, sequence-based methods for capturing the temporal evolution of user activities, and content-based models for leveraging text and visual content. However, the development of a unifying framework that integrates these diverse techniques to support multiple applications remains a significant challenge. This paper presents OmniSage, a large-scale representation framework that learns universal representations for a variety of applications at Pinterest. OmniSage integrates graph neural networks with content-based models and user sequence models by employing multiple contrastive learning tasks to effectively process graph data, user sequence data, and content signals. To support the training and inference of OmniSage, we developed an efficient infrastructure capable of supporting Pinterest graphs with billions of nodes. The universal representations generated by OmniSage have significantly enhanced user experiences on Pinterest, leading to an approximate 2.5% increase in sitewide repins (saves) across five applications. This paper highlights the impact of unifying representation learning methods, and we make the model code publicly available at https://github.com/pinterest/atg-research/tree/main/omnisage.

cs.IR↗

arXiv2025

Sounding Like a Winner? Prosodic Differences in Post-Match Interviews

This study examines the prosodic characteristics associated with winning and losing in post-match tennis interviews. Additionally, this research explores the potential to classify match outcomes solely based on post-match interview recordings using prosodic features and self-supervised learning (SSL) representations. By analyzing prosodic elements such as pitch and intensity, alongside SSL models like Wav2Vec 2.0 and HuBERT, the aim is to determine whether an athlete has won or lost their match. Traditional acoustic features and deep speech representations are extracted from the data, and machine learning classifiers are employed to distinguish between winning and losing players. Results indicate that SSL representations effectively differentiate between winning and losing outcomes, capturing subtle speech patterns linked to emotional states. At the same time, prosodic cues -- such as pitch variability -- remain strong indicators of victory.

cs.CL↗

arXiv2025

PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents

Photo retouching is integral to photographic art, extending far beyond simple technical fixes to heighten emotional expression and narrative depth. While artists leverage expertise to create unique visual effects through deliberate adjustments, non-professional users often rely on automated tools that produce visually pleasing results but lack interpretative depth and interactive transparency. In this paper, we introduce PhotoArtAgent, an intelligent system that combines Vision-Language Models (VLMs) with advanced natural language reasoning to emulate the creative process of a professional artist. The agent performs explicit artistic analysis, plans retouching strategies, and outputs precise parameters to Lightroom through an API. It then evaluates the resulting images and iteratively refines them until the desired artistic vision is achieved. Throughout this process, PhotoArtAgent provides transparent, text-based explanations of its creative rationale, fostering meaningful interaction and user control. Experimental results show that PhotoArtAgent not only surpasses existing automated tools in user studies but also achieves results comparable to those of professional human artists.

cs.CV↗

arXiv2025

Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting

Face reenactment and portrait relighting are essential tasks in portrait editing, yet they are typically addressed independently, without much synergy. Most face reenactment methods prioritize motion control and multiview consistency, while portrait relighting focuses on adjusting shading effects. To take advantage of both geometric consistency and illumination awareness, we introduce Total-Editing, a unified portrait editing framework that enables precise control over appearance, motion, and lighting. Specifically, we design a neural radiance field decoder with intrinsic decomposition capabilities. This allows seamless integration of lighting information from portrait images or HDR environment maps into synthesized portraits. We also incorporate a moving least squares based deformation field to enhance the spatiotemporal coherence of avatar motion and shading effects. With these innovations, our unified framework significantly improves the quality and realism of portrait editing results. Further, the multi-source nature of Total-Editing supports more flexible applications, such as illumination transfer from one portrait to another, or portrait animation with customized backgrounds.

cs.CV↗

arXiv2025

OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition

Multimodal Emotion Recognition (MER) is a critical research area that seeks to decode human emotions from diverse data modalities. However, existing machine learning methods predominantly rely on predefined emotion taxonomies, which fail to capture the inherent complexity, subtlety, and multi-appraisal nature of human emotional experiences, as demonstrated by studies in psychology and cognitive science. To overcome this limitation, we advocate for introducing the concept of open vocabulary into MER. This paradigm shift aims to enable models to predict emotions beyond a fixed label space, accommodating a flexible set of categories to better reflect the nuanced spectrum of human emotions. To achieve this, we propose a novel paradigm: Open-Vocabulary MER (OV-MER), which enables emotion prediction without being confined to predefined spaces. However, constructing a dataset that encompasses the full range of emotions for OV-MER is practically infeasible; hence, we present a comprehensive solution including a newly curated database, novel evaluation metrics, and a preliminary benchmark. By advancing MER from basic emotions to more nuanced and diverse emotional states, we hope this work can inspire the next generation of MER, enhancing its generalizability and applicability in real-world scenarios. Code and dataset are available at: https://github.com/zeroQiaoba/AffectGPT.

cs.HC↗

arXiv2025

AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models

The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level, from naive discriminative tasks to complex emotion understanding with advanced video understanding abilities and natural language description. However, the current community suffers from a lack of large-scale datasets with intensive, descriptive emotion annotations, as well as a multimodal-centric framework to maximize the potential of MLLMs for emotion understanding. To address this, we establish a new benchmark for MLLM-based emotion understanding with a novel dataset (MER-Caption) and a new model (AffectGPT). Utilizing our model-based crowd-sourcing data collection strategy, we construct the largest descriptive emotion dataset to date (by far), featuring over 2K fine-grained emotion categories across 115K samples. We also introduce the AffectGPT model, designed with pre-fusion operations to enhance multimodal integration. Finally, we present MER-UniBench, a unified benchmark with evaluation metrics tailored for typical MER tasks and the free-form, natural language output style of MLLMs. Extensive experimental results show AffectGPT's robust performance across various MER tasks. We have released both the code and the dataset to advance research and development in emotion understanding: https://github.com/zeroQiaoba/AffectGPT.

cs.HC↗