arXiv subjects

Jun Yu

Publications and source records attributed to Jun Yu.

At least 127 records · Page 7Linked to original sources

arXiv2025

Data-free Knowledge Distillation with Diffusion Models

Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to training data. Although diffusion models are adept at synthesizing high-fidelity photorealistic images across various domains, existing methods cannot be easiliy implemented to DFKD. To bridge that gap, this paper proposes a novel approach based on diffusion models, DiffDFKD. Specifically, DiffDFKD involves targeted optimizations in two key areas. Firstly, DiffDFKD utilizes valuable information from teacher models to guide the pre-trained diffusion models' data synthesis, generating datasets that mirror the training data distribution and effectively bridge domain gaps. Secondly, to reduce computational burdens, DiffDFKD introduces Latent CutMix Augmentation, an efficient technique, to enhance the diversity of diffusion model-generated images for DFKD while preserving key attributes for effective knowledge transfer. Extensive experiments validate the efficacy of DiffDFKD, yielding state-of-the-art results exceeding existing DFKD approaches. We release our code at https://github.com/xhqi0109/DiffDFKD.

cs.CV↗

arXiv2025

Technical Approach for the EMI Challenge in the 8th Affective Behavior Analysis in-the-Wild Competition

Emotional Mimicry Intensity (EMI) estimation plays a pivotal role in understanding human social behavior and advancing human-computer interaction. The core challenges lie in dynamic correlation modeling and robust fusion of multimodal temporal signals. To address the limitations of existing methods--insufficient exploitation of cross-modal synergies, sensitivity to noise, and constrained fine-grained alignment capabilities--this paper proposes a dual-stage cross-modal alignment framework. Stage 1 develops vision-text and audio-text contrastive learning networks based on a CLIP architecture, achieving preliminary feature-space alignment through modality-decoupled pre-training. Stage 2 introduces a temporal-aware dynamic fusion module integrating Temporal Convolutional Networks (TCN) and gated bidirectional LSTM to capture macro-evolution patterns of facial expressions and local dynamics of acoustic features, respectively. A novel quality-guided fusion strategy further enables differentiable weight allocation for modality compensation under occlusion and noise. Experiments on the Hume-Vidmimic2 dataset demonstrate superior performance with an average Pearson correlation coefficient of 0.51 across six emotion dimensions on the validate set. Remarkably, our method achieved 0.68 on the test set, securing runner-up in the EMI Challenge Track of the 8th ABAW (Affective Behavior Analysis in the Wild) Competition, offering a novel pathway for fine-grained emotion analysis in open environments.

cs.CV↗

arXiv2025

Design of an Expression Recognition Solution Based on the Global Channel-Spatial Attention Mechanism and Proportional Criterion Fusion

Facial expression recognition is a challenging classification task that holds broad application prospects in the field of human-computer interaction. This paper aims to introduce the method we will adopt in the 8th Affective and Behavioral Analysis in the Wild (ABAW) Competition, which will be held during the Conference on Computer Vision and Pattern Recognition (CVPR) in 2025.First of all, we apply the frequency masking technique and the method of extracting data at equal time intervals to conduct targeted processing on the original videos. Then, based on the residual hybrid convolutional neural network and the multi-branch convolutional neural network respectively, we design feature extraction models for image and audio sequences. In particular, we propose a global channel-spatial attention mechanism to enhance the features initially extracted from both the audio and image modalities respectively.Finally, we adopt a decision fusion strategy based on the proportional criterion to fuse the classification results of the two single modalities, obtain an emotion probability vector, and output the final emotional classification. We also design a coarse - fine granularity loss function to optimize the performance of the entire network, which effectively improves the accuracy of facial expression recognition.In the facial expression recognition task of the 8th ABAW Competition, our method ranked third on the official validation set. This result fully confirms the effectiveness and competitiveness of the method we have proposed.

cs.CV↗

arXiv2025

Solution for 8th Competition on Affective & Behavior Analysis in-the-wild

In this report, we present our solution for the Action Unit (AU) Detection Challenge, in 8th Competition on Affective Behavior Analysis in-the-wild. In order to achieve robust and accurate classification of facial action unit in the wild environment, we introduce an innovative method that leverages audio-visual multimodal data. Our method employs ConvNeXt as the image encoder and uses Whisper to extract Mel spectrogram features. For these features, we utilize a Transformer encoder-based feature fusion module to integrate the affective information embedded in audio and image features. This ensures the provision of rich high-dimensional feature representations for the subsequent multilayer perceptron (MLP) trained on the Aff-Wild2 dataset, enhancing the accuracy of AU detection.

cs.CV↗

arXiv2025

Compound Expression Recognition via Large Vision-Language Models

Compound Expression Recognition (CER) is crucial for understanding human emotions and improving human-computer interaction. However, CER faces challenges due to the complexity of facial expressions and the difficulty of capturing subtle emotional cues. To address these issues, we propose a novel approach leveraging Large Vision-Language Models (LVLMs). Our method employs a two-stage fine-tuning process: first, pre-trained LVLMs are fine-tuned on basic facial expressions to establish foundational patterns; second, the model is further optimized on a compound-expression dataset to refine visual-language feature interactions. Our approach achieves advanced accuracy on the RAF-DB dataset and demonstrates strong zero-shot generalization on the C-EXPR-DB dataset, showcasing its potential for real-world applications in emotion analysis and human-computer interaction.

cs.CV↗

arXiv2025

Interactive Multimodal Fusion with Temporal Modeling

This paper presents our method for the estimation of valence-arousal (VA) in the 8th Affective Behavior Analysis in-the-Wild (ABAW) competition. Our approach integrates visual and audio information through a multimodal framework. The visual branch uses a pre-trained ResNet model to extract spatial features from facial images. The audio branches employ pre-trained VGG models to extract VGGish and LogMel features from speech signals. These features undergo temporal modeling using Temporal Convolutional Networks (TCNs). We then apply cross-modal attention mechanisms, where visual features interact with audio features through query-key-value attention structures. Finally, the features are concatenated and passed through a regression layer to predict valence and arousal. Our method achieves competitive performance on the Aff-Wild2 dataset, demonstrating effective multimodal fusion for VA estimation in-the-wild.

cs.CV↗

arXiv2025

Towards Text-Image Interleaved Retrieval

Current multimodal information retrieval studies mainly focus on single-image inputs, which limits real-world applications involving multiple images and text-image interleaved content. In this work, we introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences, and the model is required to understand the semantics from the interleaved context for effective retrieval. We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries. To explore the task, we adapt several off-the-shelf retrievers and build a dense baseline by interleaved multimodal large language model (MLLM). We then propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity, to address the challenge of excessive visual tokens in MLLM-based TIIR models. Experiments demonstrate that simple adaption of existing models does not consistently yield effective results. Our MME achieves significant improvements over the baseline by substantially fewer visual tokens. We provide extensive analysis and will release the dataset and code to facilitate future research.

cs.CL↗

arXiv2025

FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces

Virtual film production requires intricate decision-making processes, including scriptwriting, virtual cinematography, and precise actor positioning and actions. Motivated by recent advances in automated decision-making with language agent-based societies, this paper introduces FilmAgent, a novel LLM-based multi-agent collaborative framework for end-to-end film automation in our constructed 3D virtual spaces. FilmAgent simulates various crew roles, including directors, screenwriters, actors, and cinematographers, and covers key stages of a film production workflow: (1) idea development transforms brainstormed ideas into structured story outlines; (2) scriptwriting elaborates on dialogue and character actions for each scene; (3) cinematography determines the camera setups for each shot. A team of agents collaborates through iterative feedback and revisions, thereby verifying intermediate scripts and reducing hallucinations. We evaluate the generated videos on 15 ideas and 4 key aspects. Human evaluation shows that FilmAgent outperforms all baselines across all aspects and scores 3.98 out of 5 on average, showing the feasibility of multi-agent collaboration in filmmaking. Further analysis reveals that FilmAgent, despite using the less advanced GPT-4o model, surpasses the single-agent o1, showing the advantage of a well-coordinated multi-agent system. Lastly, we discuss the complementary strengths and weaknesses of OpenAI's text-to-video model Sora and our FilmAgent in filmmaking.

cs.CL↗

arXiv2025

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model

As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data quality. In this work, we introduce KaLM-Embedding, a general multilingual embedding model that leverages a large quantity of cleaner, more diverse, and domain-specific training data. Our model has been trained with key techniques proven to enhance performance: (1) persona-based synthetic data to create diversified examples distilled from LLMs, (2) ranking consistency filtering to remove less informative samples, and (3) semi-homogeneous task batch sampling to improve training efficacy. Departing from traditional BERT-like architectures, we adopt Qwen2-0.5B as the pre-trained model, facilitating the adaptation of auto-regressive language models for general embedding tasks. Extensive evaluations of the MTEB benchmark across multiple languages show that our model outperforms others of comparable size, setting a new standard for multilingual embedding models with <1B parameters.

cs.CL↗

arXiv2024

Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering

Video Question Answering (VideoQA) represents a crucial intersection between video understanding and language processing, requiring both discriminative unimodal comprehension and sophisticated cross-modal interaction for accurate inference. Despite advancements in multi-modal pre-trained models and video-language foundation models, these systems often struggle with domain-specific VideoQA due to their generalized pre-training objectives. Addressing this gap necessitates bridging the divide between broad cross-modal knowledge and the specific inference demands of VideoQA tasks. To this end, we introduce HeurVidQA, a framework that leverages domain-specific entity-action heuristics to refine pre-trained video-language foundation models. Our approach treats these models as implicit knowledge engines, employing domain-specific entity-action prompters to direct the model's focus toward precise cues that enhance reasoning. By delivering fine-grained heuristics, we improve the model's ability to identify and interpret key entities and actions, thereby enhancing its reasoning capabilities. Extensive evaluations across multiple VideoQA datasets demonstrate that our method significantly outperforms existing models, underscoring the importance of integrating domain-specific knowledge into video-language models for more accurate and context-aware VideoQA.

cs.CV↗

arXiv2024

Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering

Long-term Video Question Answering (VideoQA) is a challenging vision-and-language bridging task focusing on semantic understanding of untrimmed long-term videos and diverse free-form questions, simultaneously emphasizing comprehensive cross-modal reasoning to yield precise answers. The canonical approaches often rely on off-the-shelf feature extractors to detour the expensive computation overhead, but often result in domain-independent modality-unrelated representations. Furthermore, the inherent gradient blocking between unimodal comprehension and cross-modal interaction hinders reliable answer generation. In contrast, recent emerging successful video-language pre-training models enable cost-effective end-to-end modeling but fall short in domain-specific ratiocination and exhibit disparities in task formulation. Toward this end, we present an entirely end-to-end solution for long-term VideoQA: Multi-granularity Contrastive cross-modal collaborative Generation (MCG) model. To derive discriminative representations possessing high visual concepts, we introduce Joint Unimodal Modeling (JUM) on a clip-bone architecture and leverage Multi-granularity Contrastive Learning (MCL) to harness the intrinsically or explicitly exhibited semantic correspondences. To alleviate the task formulation discrepancy problem, we propose a Cross-modal Collaborative Generation (CCG) module to reformulate VideoQA as a generative task instead of the conventional classification scheme, empowering the model with the capability for cross-modal high-semantic fusion and generation so as to rationalize and answer. Extensive experiments conducted on six publicly available VideoQA datasets underscore the superiority of our proposed method.

cs.CV↗

arXiv2024

Search Prominence with Costly Product Returns

Search prominence may have a detrimental impact on a firm's profits in the presence of costly product returns. We analyze the impact of search prominence on firm profitability in a duopoly search model, considering the presence of costly product returns. Consumer match values are assumed to be independently and identically distributed across the two products. Our results show that the non-prominent firm benefits from facing consumers with relatively low match values for the prominent firm's products, thus avoiding costly returns. When return costs are sufficiently high, the prominent firm may earn lower profits than its non-prominent competitor. This outcome holds under both price exogeneity and price competition. Furthermore, the profitability advantage of prominence diminishes as return costs increase. Platforms that maximize ad revenue should consider retaining positive return cost for consumers rather than fully passing it on to firms. For e-commerce platforms, it is crucial to align product return policies with broader management objectives to optimize firm profitability.

econ.TH↗

arXiv2024

Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policy

Embodied AI represents a paradigm in AI research where artificial agents are situated within and interact with physical or virtual environments. Despite the recent progress in Embodied AI, it is still very challenging to learn the generalizable manipulation skills that can handle large deformation and topological changes on soft-body objects, such as clay, water, and soil. In this work, we proposed an effective policy, namely GP2E behavior cloning policy, which can guide the agent to learn the generalizable manipulation skills from soft-body tasks, including pouring, filling, hanging, excavating, pinching, and writing. Concretely, we build our policy from three insights:(1) Extracting intricate semantic features from point cloud data and seamlessly integrating them into the robot's end-effector frame; (2) Capturing long-distance interactions in long-horizon tasks through the incorporation of our guided self-attention module; (3) Mitigating overfitting concerns and facilitating model convergence to higher accuracy levels via the introduction of our two-stage fine-tuning strategy. Through extensive experiments, we demonstrate the effectiveness of our approach by achieving the 1st prize in the soft-body track of the ManiSkill2 Challenge at the CVPR 2023 4th Embodied AI workshop. Our findings highlight the potential of our method to improve the generalization abilities of Embodied AI models and pave the way for their practical applications in real-world scenarios.

cs.RO↗

arXiv2024

NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired People

Indoor navigation is challenging due to the absence of satellite positioning. This challenge is manifold greater for Visually Impaired People (VIPs) who lack the ability to get information from wayfinding signage. Other sensor signals (e.g., Bluetooth and LiDAR) can be used to create turn-by-turn navigation solutions with position updates for users. Unfortunately, these solutions require tags to be installed all around the environment or the use of fairly expensive hardware. Moreover, these solutions require a high degree of manual involvement that raises costs, thus hampering scalability. We propose an image dataset and associated image-centric solution called NaVIP towards visual intelligence that is infrastructure-free and task-scalable, and can assist VIPs in understanding their surroundings. Specifically, we start by curating large-scale phone camera data in a four-floor research building, with 300K images, to lay the foundation for creating an image-centric indoor navigation and exploration solution for inclusiveness. Every image is labelled with precise 6DoF camera poses, details of indoor PoIs, and descriptive captions to assist VIPs. We benchmark on two main aspects: 1) positioning system and 2) exploration support, prioritizing training scalability and real-time inference, to validate the prospect of image-based solution towards indoor navigation. The dataset, code, and model checkpoints are made publicly available at https://github.com/junfish/VIP_Navi.

cs.CV↗

arXiv2024

Guided Self-attention: Find the Generalized Necessarily Distinct Vectors for Grain Size Grading

With the development of steel materials, metallographic analysis has become increasingly important. Unfortunately, grain size analysis is a manual process that requires experts to evaluate metallographic photographs, which is unreliable and time-consuming. To resolve this problem, we propose a novel classifi-cation method based on deep learning, namely GSNets, a family of hybrid models which can effectively introduce guided self-attention for classifying grain size. Concretely, we build our models from three insights:(1) Introducing our novel guided self-attention module can assist the model in finding the generalized necessarily distinct vectors capable of retaining intricate rela-tional connections and rich local feature information; (2) By improving the pixel-wise linear independence of the feature map, the highly condensed semantic representation will be captured by the model; (3) Our novel triple-stream merging module can significantly improve the generalization capability and efficiency of the model. Experiments show that our GSNet yields a classifi-cation accuracy of 90.1%, surpassing the state-of-the-art Swin Transformer V2 by 1.9% on the steel grain size dataset, which comprises 3,599 images with 14 grain size levels. Furthermore, we intuitively believe our approach is applicable to broader ap-plications like object detection and semantic segmentation.

cs.CV↗

arXiv2024

A General Framework for Producing Interpretable Semantic Text Embeddings

Semantic text embedding is essential to many tasks in Natural Language Processing (NLP). While black-box models are capable of generating high-quality embeddings, their lack of interpretability limits their use in tasks that demand transparency. Recent approaches have improved interpretability by leveraging domain-expert-crafted or LLM-generated questions, but these methods rely heavily on expert input or well-prompt design, which restricts their generalizability and ability to generate discriminative questions across a wide range of tasks. To address these challenges, we introduce \algo{CQG-MBQA} (Contrastive Question Generation - Multi-task Binary Question Answering), a general framework for producing interpretable semantic text embeddings across diverse tasks. Our framework systematically generates highly discriminative, low cognitive load yes/no questions through the \algo{CQG} method and answers them efficiently with the \algo{MBQA} model, resulting in interpretable embeddings in a cost-effective manner. We validate the effectiveness and interpretability of \algo{CQG-MBQA} through extensive experiments and ablation studies, demonstrating that it delivers embedding quality comparable to many advanced black-box models while maintaining inherently interpretability. Additionally, \algo{CQG-MBQA} outperforms other interpretable text embedding methods across various downstream tasks.

cs.CL↗

arXiv2024

The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website.

cs.CV↗

arXiv2024

Core-Elements for Large-Scale Least Squares Estimation

The coresets approach, also called subsampling or subset selection, aims to select a subsample as a surrogate for the observed sample and has found extensive applications in large-scale data analysis. Existing coresets methods construct the subsample using a subset of rows from the predictor matrix. Such methods can be significantly inefficient when the predictor matrix is sparse or numerically sparse. To overcome this limitation, we develop a novel element-wise subset selection approach, called core-elements, for large-scale least squares estimation. We provide a deterministic algorithm to construct the core-elements estimator, only requiring an $O(\mathrm{nnz}(X)+rp^2)$ computational cost, where $X$ is an $n\times p$ predictor matrix, $r$ is the number of elements selected from each column of $X$, and $\mathrm{nnz}(\cdot)$ denotes the number of non-zero elements. Theoretically, we show that the proposed estimator is unbiased and approximately minimizes an upper bound of the estimation variance. We also provide an approximation guarantee by deriving a coresets-like finite sample bound for the proposed estimator. To handle potential outliers in the data, we further combine core-elements with the median-of-means procedure, resulting in an efficient and robust estimator with theoretical consistency guarantees. Numerical studies on various synthetic and real-world datasets demonstrate the proposed method's superior performance compared to mainstream competitors.

stat.CO↗