Xiaobo Lu

Sifan Zhou, Zhi Tian, Xiangxiang Chu et al.

The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios. Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolutions (known as SPConv) to speed up training and inference, which puts a hard barrier for deployment, especially for on-device applications. In this paper, to tackle the challenge of efficient 3D object detection from an industry perspective, we devise a deployment-friendly pillar-based 3D detector, termed FastPillars. First, we introduce a novel lightweight Max-and-Attention Pillar Encoding (MAPE) module specially for enhancing small 3D objects. Second, we propose a simple yet effective principle for designing a backbone in pillar-based 3D detection. We construct FastPillars based on these designs, achieving high performance and low latency without SPConv. Extensive experiments on two large-scale datasets demonstrate the effectiveness and efficiency of FastPillars for on-device 3D detection regarding both performance and speed. Specifically, FastPillars delivers state-of-the-art accuracy on Waymo Open Dataset with 1.8X speed up and 3.8 mAPH/L2 improvement over CenterPoint (SPConv-based). Our code is publicly available at: https://github.com/StiphyJay/FastPillars.

Yichao Cao, Qingfei Tang, Xiu Su et al.

Human-object interaction (HOI) detection aims to comprehend the intricate relationships between humans and objects, predicting $<human, action, object>$ triplets, and serving as the foundation for numerous computer vision tasks. The complexity and diversity of human-object interactions in the real world, however, pose significant challenges for both annotation and recognition, particularly in recognizing interactions within an open world context. This study explores the universal interaction recognition in an open-world setting through the use of Vision-Language (VL) foundation models and large language models (LLMs). The proposed method is dubbed as \emph{\textbf{UniHOI}}. We conduct a deep analysis of the three hierarchical features inherent in visual HOI detectors and propose a method for high-level relation extraction aimed at VL foundation models, which we call HO prompt-based learning. Our design includes an HO Prompt-guided Decoder (HOPD), facilitates the association of high-level relation representations in the foundation model with various HO pairs within the image. Furthermore, we utilize a LLM (\emph{i.e.} GPT) for interaction interpretation, generating a richer linguistic understanding for complex HOIs. For open-category interaction recognition, our method supports either of two input types: interaction phrase or interpretive sentence. Our efficient architecture design and learning methods effectively unleash the potential of the VL foundation models and LLMs, allowing UniHOI to surpass all existing methods with a substantial margin, under both supervised and zero-shot settings. The code and pre-trained weights are available at: \url{https://github.com/Caoyichao/UniHOI}.

Songlin Du, Xiaoyong Lu, Yaping Yan et al.

Local feature matching plays a critical role in understanding the correspondence between cross-view images. However, traditional methods are constrained by the inherent local nature of feature descriptors, limiting their ability to capture non-local scene information that is essential for accurate cross-view correspondence. In this paper, we introduce SceneGlue, a scene-aware feature matching framework designed to overcome these limitations. SceneGlue leverages a hybridizable matching paradigm that integrates implicit parallel attention and explicit cross-view visibility estimation. The parallel attention mechanism simultaneously exchanges information among local descriptors within and across images, enhancing the scene's global context. To further enrich the scene awareness, we propose the Visibility Transformer, which explicitly categorizes features into visible and invisible regions, providing an understanding of cross-view scene visibility. By combining explicit and implicit scene-level awareness, SceneGlue effectively compensates for the local descriptor constraints. Notably, SceneGlue is trained using only local feature matches, without requiring scene-level groundtruth annotations. This scene-aware approach not only improves accuracy and robustness but also enhances interpretability compared to traditional methods. Extensive experiments on applications such as homography estimation, pose estimation, image matching, and visual localization validate SceneGlue's superior performance. The source code is available at https://github.com/songlin-du/SceneGlue.

Yichao Cao, Qingfei Tang, Feng Yang et al.

Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets. Despite the challenges posed by the numerous interaction combinations, they also offer opportunities for multimodal learning of visual texts. In this paper, we present a systematic and unified framework (RmLR) that enhances HOI detection by incorporating structured text knowledge. Firstly, we qualitatively and quantitatively analyze the loss of interaction information in the two-stage HOI detector and propose a re-mining strategy to generate more comprehensive visual representation.Secondly, we design more fine-grained sentence- and word-level alignment and knowledge transfer strategies to effectively address the many-to-many matching problem between multiple interactions and multiple texts.These strategies alleviate the matching confusion problem that arises when multiple interactions occur simultaneously, thereby improving the effectiveness of the alignment process. Finally, HOI reasoning by visual features augmented with textual knowledge substantially improves the understanding of interactions. Experimental results illustrate the effectiveness of our approach, where state-of-the-art performance is achieved on public benchmarks. We further analyze the effects of different components of our approach to provide insights into its efficacy.

Xin Lu, Shikun Chen, Yichao Cao et al.

In recent years, hashing methods have been popular in the large-scale media search for low storage and strong representation capabilities. To describe objects with similar overall appearance but subtle differences, more and more studies focus on hashing-based fine-grained image retrieval. Existing hashing networks usually generate both local and global features through attention guidance on the same deep activation tensor, which limits the diversity of feature representations. To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval. Specifically, an Attention Dispersion Loss (ADL) is designed to force the descriptors to attend to various local regions and capture diverse subtle details. Moreover, we propose a Stepwise Interactive External Attention (SIEA) to mine critical attributes in each descriptor and construct correlations between fine-grained attributes and objects. The attention mechanism is dedicated to learning discrete attributes, which will not cost additional computations in hash codes generation. Finally, the compact binary codes are learned by preserving pairwise similarities. Experimental results demonstrate that AGMH consistently yields the best performance against state-of-the-art methods on fine-grained benchmark datasets.

Sifan Zhou, Liang Li, Xinyu Zhang et al.

Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being a convenient and straightforward model compression approach, Post-Training Quantization (PTQ) has been widely adopted in 2D vision tasks. However, applying it directly to 3D lidar-based tasks inevitably leads to performance degradation. As a remedy, we propose an effective PTQ method called LiDAR-PTQ, which is particularly curated for 3D lidar detection (both SPConv-based and SPConv-free). Our LiDAR-PTQ features three main components, \textbf{(1)} a sparsity-based calibration method to determine the initialization of quantization parameters, \textbf{(2)} a Task-guided Global Positive Loss (TGPL) to reduce the disparity between the final predictions before and after quantization, \textbf{(3)} an adaptive rounding-to-nearest operation to minimize the layerwise reconstruction error. Extensive experiments demonstrate that our LiDAR-PTQ can achieve state-of-the-art quantization performance when applied to CenterPoint (both Pillar-based and Voxel-based). To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying $3\times$ inference speedup. Moreover, our LiDAR-PTQ is cost-effective being $30\times$ faster than the quantization-aware training method. Code will be released at \url{https://github.com/StiphyJay/LiDAR-PTQ}.

Shukun Jia, Shiyu Hu, Yipei Wang et al.

Referring Multi-Object Tracking (RMOT) faces a fundamental structural contradiction between the high-discriminability demand and the sparse semantic supervision. This mismatch is particularly acute in highly homogeneous scenarios that require fine-grained discrimination over complex compositional semantics. However, under sparse supervision, models overfit to salient yet insufficient cues, thereby encouraging shortcut learning and semantic collapse. To resolve this, we propose COAL (Counterfactual and Observation-enhanced Alignment Learning), a framework that advances RMOT beyond isolated structural optimization through knowledge regularization. First, we introduce Explicit Semantic Injection (ESI) via a VLM to densify the observation space and enhance instance discriminability. Second, leveraging LLM reasoning, we propose Counterfactual Learning (CFL) to augment supervision, enforcing strict attribute verification for robust compositional recognition. These strategies are unified within a Hierarchical Multi-Stream Integration (HMSI) architecture, which distills external knowledge into domain-specific discriminative representations. Experiments on Refer-KITTI and Refer-KITTI-V2 benchmarks validate COAL's efficacy. Notably, it surpasses the state-of-the-art by 7.28% HOTA on the highly challenging Refer-KITTI-V2. These results demonstrate the effectiveness of knowledge regularization for resolving the sparsity-discriminability paradox in RMOT.

Yichao Cao, Qingfei Tang, Xiaobo Lu et al.

Industrial smoke emissions present a serious threat to natural ecosystems and human health. Prior works have shown that using computer vision techniques to identify smoke is a low cost and convenient method. However, industrial smoke detection is a challenging task because industrial emission particles are often decay rapidly outside the stacks or facilities and steam is very similar to smoke. To overcome these problems, a novel Spatio-Temporal Cross Network (STCNet) is proposed to recognize industrial smoke emissions. The proposed STCNet involves a spatial pathway to extract texture features and a temporal pathway to capture smoke motion information. We assume that spatial and temporal pathway could guide each other. For example, the spatial path can easily recognize the obvious interference such as trees and buildings, and the temporal path can highlight the obscure traces of smoke movement. If the two pathways could guide each other, it will be helpful for the smoke detection performance. In addition, we design an efficient and concise spatio-temporal dual pyramid architecture to ensure better fusion of multi-scale spatiotemporal information. Finally, extensive experiments on public dataset show that our STCNet achieves clear improvements on the challenging RISE industrial smoke detection dataset against the best competitors by 6.2%. The code will be available at: https://github.com/Caoyichao/STCNet.

Shukun Jia, Shiyu Hu, Yichao Cao et al.

Multi-object tracking (MOT) is dominated by two paradigms: tracking-by-detection (TBD) and tracking-by-query (TBQ). While TBD is decoupled and efficient, its fragmented association steps and heuristic matching pipelines often compromise robustness in complex scenarios. TBQ provides stronger semantic modeling through end-to-end learning, but suffers from high training cost and slow inference due to tight coupling between detection and association. To address these challenges, we propose TBDQ-Net, a unified tracking-by-detection-and-query (TBDQ) framework that effectively combines the strengths of both paradigms. Our method efficiently integrates pretrained, high-performance detectors with an MOT-tailored associator. The associator is lightweight and directly fetches information from the inference of detectors, enhancing the overall efficiency of the framework. The associator is also learnable, making it essential for fully end-to-end optimization, ensuring robust tracking capabilities. Specifically, the associator comprises two key modules: basic information interaction (BII) for comprehensive semantic interaction, and content-position alignment (CPA) for semantic and positional consistency. TBDQ-Net's effectiveness is extensively demonstrated on DanceTrack, SportsMOT and MOT20 benchmarks. As a structurally efficient and semantically robust tracking framework, it outperforms the leading TBD method by 6.0 IDF1 points on DanceTrack and achieves at least 37.5% faster inference than prominent TBQ methods.

Sifan Zhou, Yichao Cao, Jiahao Nie et al.

3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge that limits existing trackers: (1) vast spatial redundancy from background noise impairs accuracy, and (2) informational redundancy within the foreground hinders efficiency. To tackle these issues, we propose CompTrack, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds. First, CompTrack incorporates a Spatial Foreground Predictor (SFP) module to filter out irrelevant background noise based on information entropy, addressing spatial redundancy. Subsequently, its core is an Information Bottleneck-guided Dynamic Token Compression (IB-DTC) module that eliminates the informational redundancy within the foreground. Theoretically grounded in low-rank approximation, this module leverages an online SVD analysis to adaptively compress the redundant foreground into a compact and highly informative set of proxy tokens. Extensive experiments on KITTI, nuScenes and Waymo datasets demonstrate that CompTrack achieves top-performing tracking performance with superior efficiency, running at a real-time 90 FPS on a single RTX 3090 GPU.

Yipei Wang, Shiyu Hu, Shukun Jia et al.

In this paper, we present the first systematic investigation and quantification of Similar Object Interference (SOI), a long-overlooked yet critical bottleneck in Single Object Tracking (SOT). Through controlled Online Interference Masking (OIM) experiments, we quantitatively demonstrate that eliminating interference sources leads to substantial performance improvements (AUC gains up to 4.35) across all SOTA trackers, directly validating SOI as a primary constraint for robust tracking and highlighting the feasibility of external cognitive guidance. Building upon these insights, we adopt natural language as a practical form of external guidance, and construct SOIBench-the first semantic cognitive guidance benchmark specifically targeting SOI challenges. It automatically mines SOI frames through multi-tracker collective judgment and introduces a multi-level annotation protocol to generate precise semantic guidance texts. Systematic evaluation on SOIBench reveals a striking finding: existing vision-language tracking (VLT) methods fail to effectively exploit semantic cognitive guidance, achieving only marginal improvements or even performance degradation (AUC changes of -0.26 to +0.71). In contrast, we propose a novel paradigm employing large-scale vision-language models (VLM) as external cognitive engines that can be seamlessly integrated into arbitrary RGB trackers. This approach demonstrates substantial improvements under semantic cognitive guidance (AUC gains up to 0.93), representing a significant advancement over existing VLT methods. We hope SOIBench will serve as a standardized evaluation platform to advance semantic cognitive tracking research and contribute new insights to the tracking research community.

Yang Zhang, Xin Yu, Xiaobo Lu et al.

In this paper, we study the task of hallucinating an authentic high-resolution (HR) face from an occluded thumbnail. We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN, which exploits facial geometry priors to replenish and upsample (8*) the occluded and tiny faces (16*16 pixels). Pro-UIGAN iteratively (1) estimates facial geometry priors for low-resolution (LR) faces and (2) acquires non-occluded HR face images under the guidance of the estimated priors. Our multi-stage hallucination network super-resolves and inpaints occluded LR faces in a coarse-to-fine manner, thus reducing unwanted blurriness and artifacts significantly. Specifically, we design a novel cross-modal transformer module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively. Such a design encourages joint feature learning across the input facial and landmark features, and deep feature correspondences will be discovered by attention. Thus, facial appearance features and facial geometry priors are learned in a mutual promotion manner. Extensive experiments demonstrate that our Pro-UIGAN achieves visually pleasing HR faces, reaching superior performance in downstream tasks, i.e., face alignment, face parsing, face recognition and expression classification, compared with other state-of-the-art (SotA) methods.

Yaohua Bu, Tianyi Ma, Weijun Li et al.

Second language (L2) English learners often find it difficult to improve their pronunciations due to the lack of expressive and personalized corrective feedback. In this paper, we present Pronunciation Teacher (PTeacher), a Computer-Aided Pronunciation Training (CAPT) system that provides personalized exaggerated audio-visual corrective feedback for mispronunciations. Though the effectiveness of exaggerated feedback has been demonstrated, it is still unclear how to define the appropriate degrees of exaggeration when interacting with individual learners. To fill in this gap, we interview 100 L2 English learners and 22 professional native teachers to understand their needs and experiences. Three critical metrics are proposed for both learners and teachers to identify the best exaggeration levels in both audio and visual modalities. Additionally, we incorporate the personalized dynamic feedback mechanism given the English proficiency of learners. Based on the obtained insights, a comprehensive interactive pronunciation training course is designed to help L2 learners rectify mispronunciations in a more perceptible, understandable, and discriminative manner. Extensive user studies demonstrate that our system significantly promotes the learners' learning efficiency.

Yaohua Bu, Weijun Li, Tianyi Ma et al.

To provide more discriminative feedback for the second language (L2) learners to better identify their mispronunciation, we propose a method for exaggerated visual-speech feedback in computer-assisted pronunciation training (CAPT). The speech exaggeration is realized by an emphatic speech generation neural network based on Tacotron, while the visual exaggeration is accomplished by ADC Viseme Blending, namely increasing Amplitude of movement, extending the phone's Duration and enhancing the color Contrast. User studies show that exaggerated feedback outperforms non-exaggerated version on helping learners with pronunciation identification and pronunciation improvement.

Yang Zhang, Changhui Hu, Xiaobo Lu

The technology of vehicle and driver detection in Intelligent Transportation System(ITS) is a hot topic in recent years. In particular, the driver detection is still a challenging problem which is conductive to supervising traffic order and maintaining public safety. In this paper, an algorithm based on YOLOv3 is proposed to realize the detection and classification of vehicles, drivers, and people on the highway, so as to achieve the purpose of distinguishing driver and passenger and form a one-to-one correspondence between vehicles and drivers. The proposed model and contrast experiment are conducted on our self-build traffic driver's face database. The effectiveness of our proposed algorithm is validated by extensive experiments and verified under various complex highway conditions. Compared with other advanced vehicle and driver detection technologies, the model has a good performance and is robust to road blocking, different attitudes, and extreme lighting.

Yang Zhang, Changhui Hu, Xiaobo Lu

This paper presents an novel illumination-invariant feature representation approach used to eliminate the varying illumination affection in undersampled face recognition. Firstly, a new illumination level classification technique based on Singular Value Decomposition (SVD) is proposed to judge the illumination level of input image. Secondly, we construct the logarithm edgemaps feature (LEF) based on lambertian model and local near neighbor feature of the face image, applying to local region within multiple scales. Then, the illumination level is referenced to construct the high performance LEF as well realize adaptive fusion for multiple scales LEFs for the face image, performing JLEF-feature. In addition, the constrain operation is used to remove the useless high-frequency interference, disentangling useful facial feature edges and constructing AJLEF-face. Finally, the effects of the our methods and other state-of-the-art algorithms including deep learning methods are tested on Extended Yale B, CMU PIE, AR as well as our Self-build Driver database (SDB). The experimental results demonstrate that the JLEF-feature and AJLEF-face outperform other related approaches for undersampled face recognition under varying illumination.

Yang Zhang, Changhui Hu, Xiaobo Lu

Most of current display devices are with eight or higher bit-depth. However, the quality of most multimedia tools cannot achieve this bit-depth standard for the generating images. De-quantization can improve the visual quality of low bit-depth image to display on high bit-depth screen. This paper proposes DAGAN algorithm to perform super-resolution on image intensity resolution, which is orthogonal to the spatial resolution, realizing photo-realistic de-quantization via an end-to-end learning pattern. Until now, this is the first attempt to apply Generative Adversarial Network (GAN) framework for image de-quantization. Specifically, we propose the Dense Residual Self-attention (DenseResAtt) module, which is consisted of dense residual blocks armed with self-attention mechanism, to pay more attention on high-frequency information. Moreover, the series connection of sequential DenseResAtt modules forms deep attentive network with superior discriminative learning ability in image de-quantization, modeling representative feature maps to recover as much useful information as possible. In addition, due to the adversarial learning framework can reliably produce high quality natural images, the specified content loss as well as the adversarial loss are back-propagated to optimize the training of model. Above all, DAGAN is able to generate the photo-realistic high bit-depth image without banding artifacts. Experiment results on several public benchmarks prove that the DAGAN algorithm possesses ability to achieve excellent visual effect and satisfied quantitative performance.

Chen Zhang, Xiaobo Lu, Zhiliang Huang

Researches show that fatigue driving is one of the important causes of road traffic accidents, so it is of great significance to study the driver fatigue recognition algorithm to improve road traffic safety. In recent years, with the development of deep learning, the field of pattern recognition has made great development. This paper designs a real-time fatigue state recognition algorithm based on spatio-temporal feature sequence, which can be mainly applied to the scene of fatigue driving recognition. The algorithm is divided into three task networks: face detection network, facial landmark detection and head pose estimation network, fatigue recognition network. Experiments show that the algorithm has the advantages of small volume, high speed and high accuracy.

Yang Zhang, Ivor Tsang, Yawei Luo et al.

Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in low or non-uniform illumination conditions. This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination. To this end, we develop two key components in our CPGAN: internal and external Copy and Paste nets (CPnets). Specifically, our internal CPnet exploits facial information residing in the input image to enhance facial details; while our external CPnet leverages an external HR face for illumination compensation. A new illumination compensation loss is thus developed to capture illumination from the external guided face image effectively. Furthermore, our method offsets illumination and upsamples facial details alternately in a coarse-to-fine fashion, thus alleviating the correspondence ambiguity between LR inputs and external HR inputs. Extensive experiments demonstrate that our method manifests authentic HR face images in a uniform illumination condition and outperforms state-of-the-art methods qualitatively and quantitatively.

Yang Zhang, Ivor W. Tsang, Jun Li et al.

Obtaining a high-quality frontal face image from a low-resolution (LR) non-frontal face image is primarily important for many facial analysis applications. However, mainstreams either focus on super-resolving near-frontal LR faces or frontalizing non-frontal high-resolution (HR) faces. It is desirable to perform both tasks seamlessly for daily-life unconstrained face images. In this paper, we present a novel Vivid Face Hallucination Generative Adversarial Network (VividGAN) for simultaneously super-resolving and frontalizing tiny non-frontal face images. VividGAN consists of coarse-level and fine-level Face Hallucination Networks (FHnet) and two discriminators, i.e., Coarse-D and Fine-D. The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i.e., fine-grained facial components, to attain a frontal HR face image with authentic details. In the fine-level FHnet, we also design a facial component-aware module that adopts the facial geometry guidance as clues to accurately align and merge the frontal coarse HR face and prior information. Meanwhile, two-level discriminators are designed to capture both the global outline of a face image as well as detailed facial characteristics. The Coarse-D enforces the coarsely hallucinated faces to be upright and complete while the Fine-D focuses on the fine hallucinated ones for sharper details. Extensive experiments demonstrate that our VividGAN achieves photo-realistic frontal HR faces, reaching superior performance in downstream tasks, i.e., face recognition and expression classification, compared with other state-of-the-art methods.

Shengqin Jiang, Xiaobo Lu, Yinjie Lei et al.

Crowd counting problem aims to count the number of objects within an image or a frame in the videos and is usually solved by estimating the density map generated from the object location annotations. The values in the density map, by nature, take two possible states: zero indicating no object around, a non-zero value indicating the existence of objects and the value denoting the local object density. In contrast to traditional methods which do not differentiate the density prediction of these two states, we propose to use a dedicated network branch to predict the object/non-object mask and then combine its prediction with the input image to produce the density map. Our rationale is that the mask prediction could be better modeled as a binary segmentation problem and the difficulty of estimating the density could be reduced if the mask is known. A key to the proposed scheme is the strategy of incorporating the mask prediction into the density map estimator. To this end, we study five possible solutions, and via analysis and experimental validation we identify the most effective one. Through extensive experiments on five public datasets, we demonstrate the superior performance of the proposed approach over the baselines and show that our network could achieve the state-of-the-art performance.

Yaocong Hu, MingQi Lu, Xiaobo Lu

Abnormal driving behaviour is one of the leading cause of terrible traffic accidents endangering human life. Therefore, study on driving behaviour surveillance has become essential to traffic security and public management. In this paper, we conduct this promising research and employ a two stream CNN framework for video-based driving behaviour recognition, in which spatial stream CNN captures appearance information from still frames, whilst temporal stream CNN captures motion information with pre-computed optical flow displacement between a few adjacent video frames. We investigate different spatial-temporal fusion strategies to combine the intra frame static clues and inter frame dynamic clues for final behaviour recognition. So as to validate the effectiveness of the designed spatial-temporal deep learning based model, we create a simulated driving behaviour dataset, containing 1237 videos with 6 different driving behavior for recognition. Experiment result shows that our proposed method obtains noticeable performance improvements compared to the existing methods.