arXiv subjects

Zhaozheng Yin

Publications and source records attributed to Zhaozheng Yin.

At least 19 recordsLinked to original sources

arXiv2026

GLARE: Generating Listening Heads with Appropriate Reactions

While talking head generation has advanced rapidly, generating natural listener behavior in dyadic conversations, which know when to react, how to react, and with what type of response, remains underexplored. Existing dyadic datasets lack fine-grained listener reaction annotations, and prevailing evaluation metrics inherited from talking-head and video generation measure visual realism rather than whether a listener reacted appropriately. We address these gaps along three aspects. First, we curate a listening-head-specific dataset built from RealTalk and Seamless Interaction, comprising approximately 147 hours of paired speaker-listener videos with 64,557 event-level reaction annotations across six categories: nodding, head shaking, smiling, laughing, frowning, and surprised. Second, we introduce an audio-driven baseline built on a flow-matching transformer, namely GLARE, with prosody conditioning derived from Qwen2-Audio and a temporal reaction loss that explicitly supervises frame-wise reactions. Third, we propose a reaction-oriented evaluation protocol that jointly measures reaction occurrence (R-F1), temporal alignment (R-tIoU), asymmetric temporal deviation (R-ATD), and reaction-region visual quality (R-FID), giving a more behaviorally grounded assessment than visual-quality-only metrics. Experiment results show consistent gains over prior listening-head methods in both visual fidelity and reaction-level metrics, suggesting that reaction-aware data, modeling, and evaluation are critical for natural listening behavior.

cs.CV↗

arXiv2026

Beyond Words: Multimodal LLM Knows When to Speak

Chatbots via large language models (LLMs) generate fluent responses but often struggle with when to speak, especially for brief, timely listener reactions during ongoing dialogue. We present a multimodal strategy for LLMs, which leverages synchronized video, audio, and text cues to improve conversational timing awareness. The strategy reformulates response timing as a dense response-type prediction task, enabling an agent to decide whether to remain silent, produce a short reaction, or start a full response under streaming constraints. Therefore, we introduce a curated multimodal dataset from real-world dyadic conversational videos with temporally aligned modalities and fine-grained reaction type annotations. Moreover, we design a multimodal strategy, MM-When2Speak, with a multimodal integration module on top of an LLM backbone. Experiments across various modality settings and strong LLM baselines show that MM-When2Speak achieves up to a 3x improvement in response type prediction performance, highlighting the importance of multimodal perception for natural and engaging conversational interaction.

cs.CV↗

arXiv2026

Distilling Specialized Orders for Visual Generation

Autoregressive (AR) image generators are becoming increasingly popular due to their ability to produce high-quality images and their scalability. Typical AR models are locked onto a specific generation order, often a raster-scan from top-left to bottom-right; this prohibits multi-task flexibility (inpainting, editing, outpainting) without retraining. Any-order AR models address this by learning to generate under arbitrary patch orderings, but at the cost of increased complexity and lower performance. In this paper, we present Ordered Autoregressive (OAR) generation, a self-distillation pipeline that first trains an any-order AR model, then extracts specialized generation orders from the model's own confidence scores, and fine-tunes on these orders. This achieves two goals: 1) improved generation quality by redirecting capacity from learning all $N!$ orderings to a single specialized path, and 2) preserved flexibility of any-order models. On ImageNet $256\times 256$, OAR improves FID from 2.39 to 2.17 over the any-order baseline, with consistent gains on Fashion Products and CelebA-HQ. OAR supports zero-shot inpainting and outpainting without retraining, and human evaluation shows 64% preference over the baseline. The pipeline requires only lightweight fine-tuning on a pretrained any-order model, with no architectural changes or additional annotations.

cs.CV↗

arXiv2026

CCDNet: Learning to Detect Camouflage against Distractors in Infrared Small Target Detection

Infrared target detection (IRSTD) tasks have critical applications in areas like wilderness rescue and maritime search. However, detecting infrared targets is challenging due to their low contrast and tendency to blend into complex backgrounds, effectively camouflaging themselves. Additionally, other objects with similar features (distractors) can cause false alarms, further degrading detection performance. To address these issues, we propose a novel \textbf{C}amouflage-aware \textbf{C}ounter-\textbf{D}istraction \textbf{Net}work (CCDNet) in this paper. We design a backbone with Weighted Multi-branch Perceptrons (WMPs), which aggregates self-conditioned multi-level features to accurately represent the target and background. Based on these rich features, we then propose a novel Aggregation-and-Refinement Fusion Neck (ARFN) to refine structures/semantics from shallow/deep features maps, and bidirectionally reconstruct the relations between the targets and the backgrounds, highlighting the targets while suppressing the complex backgrounds to improve detection accuracy. Furthermore, we present a new Contrastive-aided Distractor Discriminator (CaDD), enforcing adaptive similarity computation both locally and globally between the real targets and the backgrounds to more precisely discriminate distractors, so as to reduce the false alarm rate. Extensive experiments on infrared image datasets confirm that CCDNet outperforms other state-of-the-art methods.

cs.CV↗

arXiv2026

SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis

The rapid progress of text-to-image (T2I) models has unlocked unprecedented creative potential, yet their ability to faithfully render complex prompts involving multiple objects, attributes, and spatial relationships remains a significant bottleneck. Progress is hampered by a lack of adequate evaluation methods; current benchmarks are often restricted to closed-set vocabularies, lack fine-grained diagnostic capabilities, and fail to provide the interpretable feedback necessary to diagnose and remedy specific compositional failures. We solve these challenges by introducing SANEval (Spatial, Attribute, and Numeracy Evaluation), a comprehensive benchmark that establishes a scalable new pipeline for open-vocabulary compositional evaluation. SANEval combines a large language model (LLM) for deep prompt understanding with an LLM-enhanced, open-vocabulary object detector to robustly evaluate compositional adherence, unconstrained by a fixed vocabulary. Through extensive experiments on six state-of-the-art T2I models, we demonstrate that SANEval's automated evaluations provide a more faithful proxy for human assessment; our metric achieves a Spearman's rank correlation with statistically different results than those of existing benchmarks across tasks of attribute binding, spatial relations, and numeracy. To facilitate future research in compositional T2I generation and evaluation, we will release the SANEval dataset and our open-source evaluation pipeline.

cs.CV↗

arXiv2026

ASBA: A-line State Space Model and B-line Attention for Sparse Optical Doppler Tomography Reconstruction

Optical Doppler Tomography (ODT) is an emerging blood flow analysis technique. A 2D ODT image (B-scan) is generated by sequentially acquiring 1D depth-resolved raw A-scans (A-line) along the lateral axis (B-line), followed by Doppler phase-subtraction analysis. To ensure high-fidelity B-scan images, current practices rely on dense sampling, which prolongs scanning time, increases storage demands, and limits the capture of rapid blood flow dynamics. Recent studies have explored sparse sampling of raw A-scans to alleviate these limitations, but their effectiveness is hindered by the conservative sampling rates and the uniform modeling of flow and background signals. In this study, we introduce a novel blood flow-aware network, named ASBA (A-line ROI State space model and B-line phase Attention), to reconstruct ODT images from highly sparsely sampled raw A-scans. Specifically, we propose an A-line ROI state space model to extract sparsely distributed flow features along the A-line, and a B-line phase attention to capture long-range flow signals along each B-line based on phase difference. Moreover, we introduce a flow-aware weighted loss function that encourages the network to prioritize the accurate reconstruction of flow signals. Extensive experiments on real animal data demonstrate that the proposed approach clearly outperforms existing state-of-the-art reconstruction methods.

cs.CV↗

arXiv2025

Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering

Medical Visual Question Answering (Med-VQA) is a challenging task that requires a deep understanding of both medical images and textual questions. Although recent works leveraging Medical Vision-Language Pre-training (Med-VLP) have shown strong performance on the Med-VQA task, there is still no unified solution for modality alignment, and the issue of hard negatives remains under-explored. Additionally, commonly used knowledge fusion techniques for Med-VQA may introduce irrelevant information. In this work, we propose a framework to address these challenges through three key contributions: (1) a unified solution for heterogeneous modality alignments across multiple levels, modalities, views, and stages, leveraging methods like contrastive learning and optimal transport theory; (2) a hard negative mining method that employs soft labels for multi-modality alignments and enforces the hard negative pair discrimination; and (3) a Gated Cross-Attention Module for Med-VQA that integrates the answer vocabulary as prior knowledge and selects relevant information from it. Our framework outperforms the previous state-of-the-art on widely used Med-VQA datasets like RAD-VQA, SLAKE, PathVQA and VQA-2019.

cs.CV↗

arXiv2025

SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation

Domain Adaptation (DA) and Semi-supervised Learning (SSL) converge in Semi-supervised Domain Adaptation (SSDA), where the objective is to transfer knowledge from a source domain to a target domain using a combination of limited labeled target samples and abundant unlabeled target data. Although intuitive, a simple amalgamation of DA and SSL is suboptimal in semantic segmentation due to two major reasons: (1) previous methods, while able to learn good segmentation boundaries, are prone to confuse classes with similar visual appearance due to limited supervision; and (2) skewed and imbalanced training data distribution preferring source representation learning whereas impeding from exploring limited information about tailed classes. Language guidance can serve as a pivotal semantic bridge, facilitating robust class discrimination and mitigating visual ambiguities by leveraging the rich semantic relationships encoded in pre-trained language models to enhance feature representations across domains. Therefore, we propose the first language-guided SSDA setting for semantic segmentation in this work. Specifically, we harness the semantic generalization capabilities inherent in vision-language models (VLMs) to establish a synergistic framework within the SSDA paradigm. To address the inherent class-imbalance challenges in long-tailed distributions, we introduce class-balanced segmentation loss formulations that effectively regularize the learning process. Through extensive experimentation across diverse domain adaptation scenarios, our approach demonstrates substantial performance improvements over contemporary state-of-the-art (SoTA) methodologies. Code is available: \href{https://github.com/hritam-98/SemiDAViL}{GitHub}.

cs.CV↗

arXiv2024

Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors

3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Accurately reconstructing an object's complete 3D structure and texture has numerous applications in real-world scenarios, including robotic manipulation, grasping, 3D scene understanding, and AR/VR. Recent advancements in 3D object generation have introduced techniques that reconstruct an object's 3D shape and texture by optimizing the efficient representation of Gaussian Splatting, guided by pre-trained 2D or 3D diffusion models. However, a notable disparity exists between the training datasets of these models, leading to distinct differences in their outputs. While 2D models generate highly detailed visuals, they lack cross-view consistency in geometry and texture. In contrast, 3D models ensure consistency across different views but often result in overly smooth textures. We propose bridging the gap between 2D and 3D diffusion models to address this limitation by integrating a two-stage frequency-based distillation loss with Gaussian Splatting. Specifically, we leverage geometric priors in the low-frequency spectrum from a 3D diffusion model to maintain consistent geometry and use a 2D diffusion model to refine the fidelity and texture in the high-frequency spectrum of the generated 3D structure, resulting in more detailed and fine-grained outcomes. Our approach enhances geometric consistency and visual quality, outperforming the current SOTA. Additionally, we demonstrate the easy adaptability of our method for efficient object pose estimation and tracking.

cs.CV↗

arXiv2024

Advancements in Repetitive Action Counting: Joint-Based PoseRAC Model With Improved Performance

Repetitive counting (RepCount) is critical in various applications, such as fitness tracking and rehabilitation. Previous methods have relied on the estimation of red-green-and-blue (RGB) frames and body pose landmarks to identify the number of action repetitions, but these methods suffer from a number of issues, including the inability to stably handle changes in camera viewpoints, over-counting, under-counting, difficulty in distinguishing between sub-actions, inaccuracy in recognizing salient poses, etc. In this paper, based on the work done by [1], we integrate joint angles with body pose landmarks to address these challenges and achieve better results than the state-of-the-art RepCount methods, with a Mean Absolute Error (MAE) of 0.211 and an Off-By-One (OBO) counting accuracy of 0.599 on the RepCount data set [2]. Comprehensive experimental results demonstrate the effectiveness and robustness of our method.

cs.CV↗

arXiv2024

Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for Automated Structural Condition Assessment in Visual Inspection

Efficiently monitoring the condition of civil infrastructure requires automating the structural condition assessment in visual inspection. This paper proposes an Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for automatic structural condition assessment in visual bridge inspection. AECIF-Net can simultaneously parse structural elements and segment surface defects on the elements in inspection images. It integrates two task-specific relearning subnets to extract task-specific features from an overall feature embedding. A co-interactive feature fusion module further captures the spatial correlation and facilitates information sharing between tasks. Experimental results demonstrate that the proposed AECIF-Net outperforms the current state-of-the-art approaches, achieving promising performance with 92.11% mIoU for element segmentation and 87.16% mIoU for corrosion segmentation on the test set of the new benchmark dataset Steel Bridge Condition Inspection Visual (SBCIV). An ablation study verifies the merits of the designs for AECIF-Net, and a case study demonstrates its capability to automate structural condition assessment.

cs.CV↗

arXiv2023

CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation

While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes, masks, and cell types for every cell in every image, to fine-tune the pre-trained model. To lower the cost of annotation, this work considers the problem of pre-training DNN models for few-shot cell segmentation, where massive unlabeled cell images are available but only a small proportion is annotated. Hereby, we propose Cross-domain Unsupervised Pre-training, namely CUPre, transferring the capability of object detection and instance segmentation for common visual objects (learned from COCO) to the visual domain of cells using unlabeled images. Given a standard COCO pre-trained network with backbone, neck, and head modules, CUPre adopts an alternate multi-task pre-training (AMT2) procedure with two sub-tasks -- in every iteration of pre-training, AMT2 first trains the backbone with cell images from multiple cell datasets via unsupervised momentum contrastive learning (MoCo) [3], and then trains the whole model with vanilla COCO datasets via instance segmentation. After pre-training, CUPre fine-tunes the whole model on the cell segmentation task using a few annotated images. We carry out extensive experiments to evaluate CUPre using LIVECell [2] and BBBC038 [4] datasets in few-shot instance segmentation settings. The experiment shows that CUPre can outperform existing pre-training methods, achieving the highest average precision (AP) for few-shot cell segmentation and detection.

cs.CV↗

arXiv2023

Semi-supervised Domain Adaptive Medical Image Segmentation through Consistency Regularized Disentangled Contrastive Learning

Although unsupervised domain adaptation (UDA) is a promising direction to alleviate domain shift, they fall short of their supervised counterparts. In this work, we investigate relatively less explored semi-supervised domain adaptation (SSDA) for medical image segmentation, where access to a few labeled target samples can improve the adaptation performance substantially. Specifically, we propose a two-stage training process. First, an encoder is pre-trained in a self-learning paradigm using a novel domain-content disentangled contrastive learning (CL) along with a pixel-level feature consistency constraint. The proposed CL enforces the encoder to learn discriminative content-specific but domain-invariant semantics on a global scale from the source and target images, whereas consistency regularization enforces the mining of local pixel-level information by maintaining spatial sensitivity. This pre-trained encoder, along with a decoder, is further fine-tuned for the downstream task, (i.e. pixel-level segmentation) using a semi-supervised setting. Furthermore, we experimentally validate that our proposed method can easily be extended for UDA settings, adding to the superiority of the proposed strategy. Upon evaluation on two domain adaptive image segmentation tasks, our proposed method outperforms the SoTA methods, both in SSDA and UDA settings. Code is available at https://github.com/hritam-98/GFDA-disentangled

cs.CV↗

arXiv2022

An Attention-guided Multistream Feature Fusion Network for Localization of Risky Objects in Driving Videos

Detecting dangerous traffic agents in videos captured by vehicle-mounted dashboard cameras (dashcams) is essential to facilitate safe navigation in a complex environment. Accident-related videos are just a minor portion of the driving video big data, and the transient pre-accident processes are highly dynamic and complex. Besides, risky and non-risky traffic agents can be similar in their appearance. These make risky object localization in the driving video particularly challenging. To this end, this paper proposes an attention-guided multistream feature fusion network (AM-Net) to localize dangerous traffic agents from dashcam videos. Two Gated Recurrent Unit (GRU) networks use object bounding box and optical flow features extracted from consecutive video frames to capture spatio-temporal cues for distinguishing dangerous traffic agents. An attention module coupled with the GRUs learns to attend to the traffic agents relevant to an accident. Fusing the two streams of features, AM-Net predicts the riskiness scores of traffic agents in the video. In supporting this study, the paper also introduces a benchmark dataset called Risky Object Localization (ROL). The dataset contains spatial, temporal, and categorical annotations with the accident, object, and scene-level attributes. The proposed AM-Net achieves a promising performance of 85.73% AUC on the ROL dataset. Meanwhile, the AM-Net outperforms current state-of-the-art for video anomaly detection by 6.3% AUC on the DoTA dataset. A thorough ablation study further reveals AM-Net's merits by evaluating the contributions of its different components.

cs.CV↗

arXiv2022

A Deep Neural Network for Multiclass Bridge Element Parsing in Inspection Image Analysis

Aerial robots such as drones have been leveraged to perform bridge inspections. Inspection images with both recognizable structural elements and apparent surface defects can be collected by onboard cameras to provide valuable information for the condition assessment. This article aims to determine a suitable deep neural network (DNN) for parsing multiclass bridge elements in inspection images. An extensive set of quantitative evaluations along with qualitative examples show that High-Resolution Net (HRNet) possesses the desired ability. With data augmentation and a training sample of 130 images, a pre-trained HRNet is efficiently transferred to the task of structural element parsing and has achieved a 92.67% mean F1-score and 86.33% mean IoU.

cs.CV↗

arXiv2021

A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents

The rapid advancement of sensor technologies and artificial intelligence are creating new opportunities for traffic safety enhancement. Dashboard cameras (dashcams) have been widely deployed on both human driving vehicles and automated driving vehicles. A computational intelligence model that can accurately and promptly predict accidents from the dashcam video will enhance the preparedness for accident prevention. The spatial-temporal interaction of traffic agents is complex. Visual cues for predicting a future accident are embedded deeply in dashcam video data. Therefore, the early anticipation of traffic accidents remains a challenge. Inspired by the attention behavior of humans in visually perceiving accident risks, this paper proposes a Dynamic Spatial-Temporal Attention (DSTA) network for the early accident anticipation from dashcam videos. The DSTA-network learns to select discriminative temporal segments of a video sequence with a Dynamic Temporal Attention (DTA) module. It also learns to focus on the informative spatial regions of frames with a Dynamic Spatial Attention (DSA) module. A Gated Recurrent Unit (GRU) is trained jointly with the attention modules to predict the probability of a future accident. The evaluation of the DSTA-network on two benchmark datasets confirms that it has exceeded the state-of-the-art performance. A thorough ablation study that assesses the DSTA-network at the component level reveals how the network achieves such performance. Furthermore, this paper proposes a method to fuse the prediction scores from two complementary models and verifies its effectiveness in further boosting the performance of early accident anticipation.

cs.CV↗

arXiv2021

A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos

Bridge inspection is an important step in preserving and rehabilitating transportation infrastructure for extending their service lives. The advancement of mobile robotic technology allows the rapid collection of a large amount of inspection video data. However, the data are mainly images of complex scenes, wherein a bridge of various structural elements mix with a cluttered background. Assisting bridge inspectors in extracting structural elements of bridges from the big complex video data, and sorting them out by classes, will prepare inspectors for the element-wise inspection to determine the condition of bridges. This paper is motivated to develop an assistive intelligence model for segmenting multiclass bridge elements from inspection videos captured by an aerial inspection platform. With a small initial training dataset labeled by inspectors, a Mask Region-based Convolutional Neural Network (Mask R-CNN) pre-trained on a large public dataset was transferred to the new task of multiclass bridge element segmentation. Besides, the temporal coherence analysis attempts to recover false negatives and identify the weakness that the neural network can learn to improve. Furthermore, a semi-supervised self-training (S$^3$T) method was developed to engage experienced inspectors in refining the network iteratively. Quantitative and qualitative results from evaluating the developed deep neural network demonstrate that the proposed method can utilize a small amount of time and guidance from experienced inspectors (3.58 hours for labeling 66 images) to build the network of excellent performance (91.8% precision, 93.6% recall, and 92.7% f1-score). Importantly, the paper illustrates an approach to leveraging the domain knowledge and experiences of bridge professionals into computational intelligence models to efficiently adapt the models to varied bridges in the National Bridge Inventory.

cs.CV↗

arXiv2021

A system of vision sensor based deep neural networks for complex driving scene analysis in support of crash risk assessment and prevention

To assist human drivers and autonomous vehicles in assessing crash risks, driving scene analysis using dash cameras on vehicles and deep learning algorithms is of paramount importance. Although these technologies are increasingly available, driving scene analysis for this purpose still remains a challenge. This is mainly due to the lack of annotated large image datasets for analyzing crash risk indicators and crash likelihood, and the lack of an effective method to extract lots of required information from complex driving scenes. To fill the gap, this paper develops a scene analysis system. The Multi-Net of the system includes two multi-task neural networks that perform scene classification to provide four labels for each scene. The DeepLab v3 and YOLO v3 are combined by the system to detect and locate risky pedestrians and the nearest vehicles. All identified information can provide the situational awareness to autonomous vehicles or human drivers for identifying crash risks from the surrounding traffic. To address the scarcity of annotated image datasets for studying traffic crashes, two completely new datasets have been developed by this paper and made available to the public, which were proved to be effective in training the proposed deep neural networks. The paper further evaluates the performance of the Multi-Net and the efficiency of the developed system. Comprehensive scene analysis is further illustrated with representative examples. Results demonstrate the effectiveness of the developed system and datasets for driving scene analysis, and their supportiveness for crash risk assessment and crash prevention.

cs.CV↗