arXiv subjects

Ying Deng

Publications and source records attributed to Ying Deng.

11 recordsLinked to original sources

arXiv2026

RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation

Reference-driven image generation has made rapid progress on identity preservation, but reliable viewpoint control across different subjects remains poorly understood. The difficulty is not merely generating a new image of the target subject: the model must infer the implicit viewpoint of one subject and transfer it to another subject using only image-level evidence, without camera poses, depth, or ray-based conditions. In this setting, existing generators conditioned on multiple image references often rely on spurious semantic correlations, which lead to viewpoint drift, part-level structural mismatches, and missing or unsupported target-specific content. We formulate this challenge as cross-subject viewpoint alignment and propose RAVA, a retrieval-augmented framework that supplies explicit geometric evidence before generation. RAVA first learns a cross-instance viewpoint embedding that retrieves target-subject images aligned with the anchor viewpoint, then applies a LogDet-based subset selection strategy to retain a compact reference set that is both view-consistent and structurally complementary. The selected references are finally consumed by a fine-tuned multi-reference image generator. Experiments show that generic semantic embeddings are nearly random for this task, while the proposed retriever substantially improves viewpoint retrieval quality. On cross-subject generation, RAVA consistently outperforms zero-shot baselines and stronger retrieval alternatives under the same generation backbone. These results indicate that cross-subject viewpoint alignment benefits from retrieval-augmented geometric grounding rather than relying on end-to-end generation alone.

cs.CV↗

arXiv2025

F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model

Traditional dialogue retrieval aims to select the most appropriate utterance or image from recent dialogue history. However, they often fail to meet users' actual needs for revisiting semantically coherent content scattered across long-form conversations. To fill this gap, we define the Fine-grained Fragment Retrieval (FFR) task, requiring models to locate query-relevant fragments, comprising both utterances and images, from multimodal long-form dialogues. As a foundation for FFR, we construct MLDR, the longest-turn multimodal dialogue retrieval dataset to date, averaging 25.45 turns per dialogue, with each naturally spanning three distinct topics. To evaluate generalization in real-world scenarios, we curate and annotate a WeChat-based test set comprising real-world multimodal dialogues with an average of 75.38 turns. Building on these resources, we explore existing generation-based Vision-Language Models (VLMs) on FFR and observe that they often retrieve incoherent utterance-image fragments. While optimized for generating responses from visual-textual inputs, these models lack explicit supervision to ensure semantic coherence within retrieved fragments. To this end, we propose F2RVLM, a generative retrieval model trained in a two-stage paradigm: (1) supervised fine-tuning to inject fragment-level retrieval knowledge, and (2) GRPO-based reinforcement learning with multi-objective rewards promoting semantic precision, relevance, and contextual coherence. To handle varying intra-fragment complexity, from locally dense to sparsely distributed, we introduce difficulty-aware curriculum sampling that ranks training instances by model-predicted difficulty and gradually exposes the model to harder samples. This boosts reasoning ability in long, multi-turn contexts. F2RVLM outperforms popular VLMs in both in-domain and real-domain settings, demonstrating superior retrieval performance.

cs.CV↗

arXiv2025

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets

Vision-language models (VLMs) often struggle with compositional reasoning due to insufficient high-quality image-text data. To tackle this challenge, we propose a novel block-based diffusion approach that automatically generates counterfactual datasets without manual annotation. Our method utilizes large language models to identify entities and their spatial relationships. It then independently generates image blocks as "puzzle pieces" coherently arranged according to specified compositional rules. This process creates diverse, high-fidelity counterfactual image-text pairs with precisely controlled variations. In addition, we introduce a specialized loss function that differentiates inter-set from intra-set samples, enhancing training efficiency and reducing the need for negative samples. Experiments demonstrate that fine-tuning VLMs with our counterfactual datasets significantly improves visual reasoning performance. Our approach achieves state-of-the-art results across multiple benchmarks while using substantially less training data than existing methods.

cs.CV↗

arXiv2025

From Imitation to Innovation: The Emergence of AI Unique Artistic Styles and the Challenge of Copyright Protection

Current legal frameworks consider AI-generated works eligible for copyright protection when they meet originality requirements and involve substantial human intellectual input. However, systematic legal standards and reliable evaluation methods for AI art copyrights are lacking. Through comprehensive analysis of legal precedents, we establish three essential criteria for determining distinctive artistic style: stylistic consistency, creative uniqueness, and expressive accuracy. To address these challenges, we introduce ArtBulb, an interpretable and quantifiable framework for AI art copyright judgment that combines a novel style description-based multimodal clustering method with multimodal large language models (MLLMs). We also present AICD, the first benchmark dataset for AI art copyright annotated by artists and legal experts. Experimental results demonstrate that ArtBulb outperforms existing models in both quantitative and qualitative evaluations. Our work aims to bridge the gap between the legal and technological communities and bring greater attention to the societal issue of AI art copyrights.

cs.CV↗

arXiv2025

RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation

Recently, significant advancements have been achieved in video generation technology, but applying it to resource-constrained downstream tasks like multi-frame animated sticker generation (ASG) characterized by low frame rates, abstract semantics, and long tail frame length distribution-remains challenging. Parameter-efficient fine-tuning (PEFT) techniques (e.g., Adapter, LoRA) for large pre-trained models suffer from insufficient fitting ability and source-domain knowledge interference. In this paper, we propose Resource-Efficient Dual-Mask Training Framework (RDTF), a dedicated solution for multi-frame ASG task under resource constraints. We argue that training a compact model from scratch with million-level samples outperforms PEFT on large models, with RDTF realizing this via three core designs: 1) a Discrete Frame Generation Network (DFGN) optimized for low-frame-rate ASG, ensuring parameter efficiency; 2) a dual-mask based data utilization strategy to enhance the availability and diversity of limited data; 3) a difficulty-adaptive curriculum learning method that decomposes sample entropy into static and adaptive components, enabling easy-to-difficult training convergence. To provide high-quality data support for RDTFs training from scratch, we construct VSD2M-a million-level multi-modal animated sticker dataset with rich annotations (static and animated stickers, action-focused text descriptions)-filling the gap of dedicated animated data for ASG task. Experiments demonstrate that RDTF is quantitatively and qualitatively superior to state-of-the-art PEFT methods (e.g., I2V-Adapter, SimDA) on ASG tasks, verifying the feasibility of our framework under resource constraints.

cs.MM↗

arXiv2024

WalkVLM:Aid Visually Impaired People Walking by Vision Language Model

Approximately 200 million individuals around the world suffer from varying degrees of visual impairment, making it crucial to leverage AI technology to offer walking assistance for these people. With the recent progress of vision-language models (VLMs), applying VLMs to offer walking guidance has become popular. However, the existing methods of walking guidance are mainly based on self-curated question-answering datasets that are not publicly accessible, without a standardized benchmark for training or evaluation. Moreover, walking assistance often requires real-time streaming video analysis and the generation of concise yet informative reminders, making VLMs struggle due to excessive responses and low efficiency in inferences. In this paper, we introduce the first large-scale dataset dedicated to walking assistance, comprising 12,000 video-annotation pairs, to provide a unified benchmark for training and evaluating systems to help visually-impaired individuals walk. Furthermore, a WalkVLM model is proposed, which employs chain of thought for hierarchical planning to generate concise but informative reminders and utilizes temporal-aware adaptive prediction to reduce the temporal redundancy of reminders. Finally, we have established a solid benchmark for blind walking task and verified the advantages of WalkVLM in stream video processing for this task compared to other VLMs. Our dataset and code are available at https://walkvlm2024.github.io.

cs.CV↗

arXiv2024

VSD2M: A Large-scale Vision-language Sticker Dataset for Multi-frame Animated Sticker Generation

As a common form of communication in social media,stickers win users' love in the internet scenarios, for their ability to convey emotions in a vivid, cute, and interesting way. People prefer to get an appropriate sticker through retrieval rather than creation for the reason that creating a sticker is time-consuming and relies on rule-based creative tools with limited capabilities. Nowadays, advanced text-to-video algorithms have spawned numerous general video generation systems that allow users to customize high-quality, photo-realistic videos by only providing simple text prompts. However, creating customized animated stickers, which have lower frame rates and more abstract semantics than videos, is greatly hindered by difficulties in data acquisition and incomplete benchmarks. To facilitate the exploration of researchers in animated sticker generation (ASG) field, we firstly construct the currently largest vision-language sticker dataset named VSD2M at a two-million scale that contains static and animated stickers. Secondly, to improve the performance of traditional video generation methods on ASG tasks with discrete characteristics, we propose a Spatial Temporal Interaction (STI) layer that utilizes semantic interaction and detail preservation to address the issue of insufficient information utilization. Moreover, we train baselines with several video generation methods (e.g., transformer-based, diffusion-based methods) on VSD2M and conduct a detailed analysis to establish systemic supervision on ASG task. To the best of our knowledge, this is the most comprehensive large-scale benchmark for multi-frame animated sticker generation, and we hope this work can provide valuable inspiration for other scholars in intelligent creation.

cs.HC↗

arXiv2024

Mobius: A High Efficient Spatial-Temporal Parallel Training Paradigm for Text-to-Video Generation Task

Inspired by the success of the text-to-image (T2I) generation task, many researchers are devoting themselves to the text-to-video (T2V) generation task. Most of the T2V frameworks usually inherit from the T2I model and add extra-temporal layers of training to generate dynamic videos, which can be viewed as a fine-tuning task. However, the traditional 3D-Unet is a serial mode and the temporal layers follow the spatial layers, which will result in high GPU memory and training time consumption according to its serial feature flow. We believe that this serial mode will bring more training costs with the large diffusion model and massive datasets, which are not environmentally friendly and not suitable for the development of the T2V. Therefore, we propose a highly efficient spatial-temporal parallel training paradigm for T2V tasks, named Mobius. In our 3D-Unet, the temporal layers and spatial layers are parallel, which optimizes the feature flow and backpropagation. The Mobius will save 24% GPU memory and 12% training time, which can greatly improve the T2V fine-tuning task and provide a novel insight for the AIGC community. We will release our codes in the future.

cs.CV↗

arXiv2024

Room-temperature sub-100 nm N\'eel-type skyrmions in non-stoichiometric van der Waals ferromagnet $\rm Fe_{3-x}GaTe_{2}$ with ultrafast laser writability

Realizing room-temperature magnetic skyrmions in two-dimensional van der Waals ferromagnets offers unparalleled prospects for future spintronic applications. However, due to the intrinsic spin fluctuations that suppress atomic long-range magnetic order and the inherent inversion crystal symmetry that excludes the presence of the Dzyaloshinskii-Moriya interaction, achieving room-temperature skyrmions in 2D magnets remains a formidable challenge. In this study, we target room-temperature 2D magnet $\rm Fe_3GaTe_2$ and unveil that the introduction of iron-deficient into this compound enables spatial inversion symmetry breaking, thus inducing a significant Dzyaloshinskii-Moriya interaction that brings about room-temperature N\'eel-type skyrmions with unprecedentedly small size. To further enhance the practical applications of this finding, we employ a homemade in-situ optical Lorentz transmission electron microscopy to demonstrate ultrafast writing of skyrmions in $\rm Fe_{3-x}GaTe_2$ using a single femtosecond laser pulse. Our results manifest the $\rm Fe_{3-x}GaTe_2$ as a promising building block for realizing skyrmion-based magneto-optical functionalities.

cond-mat.mtrl-sci↗

arXiv2021

Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features. In this work, we propose a novel Channel-wise Topology Refinement Graph Convolution (CTR-GC) to dynamically learn different topologies and effectively aggregate joint features in different channels for skeleton-based action recognition. The proposed CTR-GC models channel-wise topologies through learning a shared topology as a generic prior for all channels and refining it with channel-specific correlations for each channel. Our refinement method introduces few extra parameters and significantly reduces the difficulty of modeling channel-wise topologies. Furthermore, via reformulating graph convolutions into a unified form, we find that CTR-GC relaxes strict constraints of graph convolutions, leading to stronger representation capability. Combining CTR-GC with temporal modeling modules, we develop a powerful graph convolutional network named CTR-GCN which notably outperforms state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

cs.CV↗

arXiv2021

Open-book Video Captioning with Retrieve-Copy-Generate Network

Due to the rapid emergence of short videos and the requirement for content understanding and creation, the video captioning task has received increasing attention in recent years. In this paper, we convert traditional video captioning task into a new paradigm, \ie, Open-book Video Captioning, which generates natural language under the prompts of video-content-relevant sentences, not limited to the video itself. To address the open-book video captioning problem, we propose a novel Retrieve-Copy-Generate network, where a pluggable video-to-text retriever is constructed to retrieve sentences as hints from the training corpus effectively, and a copy-mechanism generator is introduced to extract expressions from multi-retrieved sentences dynamically. The two modules can be trained end-to-end or separately, which is flexible and extensible. Our framework coordinates the conventional retrieval-based methods with orthodox encoder-decoder methods, which can not only draw on the diverse expressions in the retrieved sentences but also generate natural and accurate content of the video. Extensive experiments on several benchmark datasets show that our proposed approach surpasses the state-of-the-art performance, indicating the effectiveness and promising of the proposed paradigm in the task of video captioning.

cs.CV↗