Tianrui Liu

Qingjie Meng, Chen Qin, Wenjia Bai et al.

Recovering the 3D motion of the heart from cine cardiac magnetic resonance (CMR) imaging enables the assessment of regional myocardial function and is important for understanding and analyzing cardiovascular disease. However, 3D cardiac motion estimation is challenging because the acquired cine CMR images are usually 2D slices which limit the accurate estimation of through-plane motion. To address this problem, we propose a novel multi-view motion estimation network (MulViMotion), which integrates 2D cine CMR images acquired in short-axis and long-axis planes to learn a consistent 3D motion field of the heart. In the proposed method, a hybrid 2D/3D network is built to generate dense 3D motion fields by learning fused representations from multi-view images. To ensure that the motion estimation is consistent in 3D, a shape regularization module is introduced during training, where shape information from multi-view images is exploited to provide weak supervision to 3D motion estimation. We extensively evaluate the proposed method on 2D cine CMR images from 580 subjects of the UK Biobank study for 3D motion tracking of the left ventricular myocardium. Experimental results show that the proposed method quantitatively and qualitatively outperforms competing methods.

Qingjie Meng, Wenjia Bai, Tianrui Liu et al.

3D motion estimation from cine cardiac magnetic resonance (CMR) images is important for the assessment of cardiac function and diagnosis of cardiovascular diseases. Most of the previous methods focus on estimating pixel-/voxel-wise motion fields in the full image space, which ignore the fact that motion estimation is mainly relevant and useful within the object of interest, e.g., the heart. In this work, we model the heart as a 3D geometric mesh and propose a novel deep learning-based method that can estimate 3D motion of the heart mesh from 2D short- and long-axis CMR images. By developing a differentiable mesh-to-image rasterizer, the method is able to leverage the anatomical shape information from 2D multi-view CMR images for 3D motion estimation. The differentiability of the rasterizer enables us to train the method end-to-end. One advantage of the proposed method is that by tracking the motion of each vertex, it is able to keep the vertex correspondence of 3D meshes between time frames, which is important for quantitative assessment of the cardiac function on the mesh. We evaluate the proposed method on CMR images acquired from the UK Biobank study. Experimental results show that the proposed method quantitatively and qualitatively outperforms both conventional and learning-based cardiac motion tracking methods.

Zhipeng Luo, Changqing Zhou, Liang Pan et al.

With the prevalence of LiDAR sensors in autonomous driving, 3D object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames given an object template. Motivated by the success of transformers, we propose Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations. PTTR consists of three novel designs. 1) Instead of random sampling, we design Relation-Aware Sampling to preserve relevant points to the given template during subsampling. 2) We propose a Point Relation Transformer for effective feature aggregation and feature matching between the template and search region. 3) Based on the coarse tracking results, we employ a novel Prediction Refinement Module to obtain the final refined prediction through local feature pooling. In addition, motivated by the favorable properties of the Bird's-Eye View (BEV) of point clouds in capturing object motion, we further design a more advanced framework named PTTR++, which incorporates both the point-wise view and BEV representation to exploit their complementary effect in generating high-quality tracking results. PTTR++ substantially boosts the tracking performance on top of PTTR with low computational overhead. Extensive experiments over multiple datasets show that our proposed approaches achieve superior 3D tracking accuracy and efficiency.

Zhipeng Luo, Gongjie Zhang, Changqing Zhou et al.

3D object detection using point clouds has attracted increasing attention due to its wide applications in autonomous driving and robotics. However, most existing studies focus on single point cloud frames without harnessing the temporal information in point cloud sequences. In this paper, we design TransPillars, a novel transformer-based feature aggregation technique that exploits temporal features of consecutive point cloud frames for multi-frame 3D object detection. TransPillars aggregates spatial-temporal point cloud features from two perspectives. First, it fuses voxel-level features directly from multi-frame feature maps instead of pooled instance features to preserve instance details with contextual information that are essential to accurate object localization. Second, it introduces a hierarchical coarse-to-fine strategy to fuse multi-scale features progressively to effectively capture the motion of moving objects and guide the aggregation of fine features. Besides, a variant of deformable transformer is introduced to improve the effectiveness of cross-frame feature matching. Extensive experiments show that our proposed TransPillars achieves state-of-art performance as compared to existing multi-frame detection approaches. Code will be released.

Zengyi Qin, Jinyuan Chen, Yunze Man et al.

Training computer use agents requires full-featured OS sandboxes with GUI environments, which consume substantial hardware resources as the number of sandboxes scales. Stochastic errors arising from diverse software execution within these sandboxes further demand robust infrastructure design and reliable error recovery. We present OSGym, a scalable OS environment infrastructure for computer use agents, built around these key optimization strategies: (1) Decentralized OS state management, which isolates failures to individual replicas and significantly enhances overall system reliability; (2) Hardware-aware OS replica orchestration, which addresses CPU-bounded scaling bottlenecks and substantially reduces compute overhead; (3) KVM virtualization with copy-on-write disk management, which shares a common bootable disk across VM instances and provisions only instance-specific modifications, reducing physical disk consumption by 88% and increasing disk provisioning speed by 37 times; and (4) Robust container pool with multi-layer fault recovery. Together, these optimizations yield strong scalability and resource efficiency: OSGym manages over a thousand OS replicas under constrained resources, supports parallel trajectory generation at 1420 multi-turn trajectories per minute, and reduces per-replica cost to 0.2-0.3 USD per day, a 90% reduction over standard deployment. Our experiments validate OSGym across end-to-end pipelines for data collection and training for computer use agents. We believe OSGym establishes a new foundation for scalable, general-purpose computer use agent research.

Junjie Zhao, Jingyi Liang, Zhenyang Cai et al.

While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplored, particularly in dentistry. Here we introduce GlobalDentBench, the first multinational dental benchmark, featuring a taxonomy that encompasses 14 dental specialties across 88 countries and regions spanning six continents. The benchmark comprises 8,978 expert-validated questions across three formats (multiple-choice, short-answer, and case-based questions) and assesses three progressive reasoning levels: knowledge recall (L1), routine reasoning (L2), and individualized reasoning (L3). To ensure data quality, the automated construction framework was calibrated by six senior dentists, achieving expert agreement rates of 99.98% for multiple-choice and short-answer questions and 96.78% for the more complex case-based questions. Evaluation of 12 frontier LLMs on GlobalDentBench revealed a sharp, stepwise performance degradation with increasing reasoning complexity. Specifically, accuracy plummeted from 81.34% on multiple-choice to 64.53% on short-answer and 22.34% on case-based questions, while declining markedly from 74.01% at L1 to 55.64% at L2 and 35.71% at L3. More critically, risk analysis of real-world dental cases demonstrated an alarming overall unsafe rate of 31.01% in LLM-generated clinical recommendations, with 4.51% posing risks of irreversible patient harm and risks particularly pronounced in specialties such as orthodontics. These findings expose fundamental limitations in the medical reasoning and safety of current LLMs. Consequently, GlobalDentBench provides a scalable foundation for trustworthy clinical AI evaluation, underscoring the urgent need for rigorous validation before the safe deployment of these models in healthcare.

Yixi Chen, Weixuan Liang, Tianrui Liu et al.

Kernel power $k$-means (KPKM) leverages a family of means to mitigate local minima issues in kernel $k$-means. However, KPKM faces two key limitations: (1) the computational burden of the full kernel matrix restricts its use on extensive data, and (2) the lack of authentic centroid-sample assignment learning reduces its noise robustness. To overcome these challenges, we propose RFF-KPKM, introducing the first approximation theory for applying random Fourier features (RFF) to KPKM. RFF-KPKM employs RFF to generate efficient, low-dimensional feature maps, bypassing the need for the whole kernel matrix. Crucially, we are the first to establish strong theoretical guarantees for this combination: (1) an excess risk bound of $\mathcal{O}(\sqrt{k^3/n})$, (2) strong consistency with membership values, and (3) a $(1+\varepsilon)$ relative error bound achievable using the RFF of dimension $\mathrm{poly}(\varepsilon^{-1}\log k)$. Furthermore, to improve robustness and the ability to learn multiple kernels, we propose IP-RFF-MKPKM, an improved possibilistic RFF-based multiple kernel power $k$-means. IP-RFF-MKPKM ensures the scalability of MKPKM via RFF and refines cluster assignments by combining the merits of the possibilistic membership and fuzzy membership. Experiments on large-scale datasets demonstrate the superior efficiency and clustering accuracy of the proposed methods compared to the state-of-the-art alternatives.

Ashwin Nair, Zhen Rong Goh, Tianrui Liu et al.

Current metadata creation for web archives is time consuming and costly due to reliance on human effort. This paper explores the use of gpt-4o for metadata generation within the Web Archive Singapore, focusing on scalability, efficiency, and cost effectiveness. We processed 112 Web ARChive (WARC) files using data reduction techniques, achieving a notable 99.9% reduction in metadata generation costs. By prompt engineering, we generated titles and abstracts, which were evaluated both intrinsically using Levenshtein Distance and BERTScore, and extrinsically with human cataloguers using McNemar's test. Results indicate that while our method offers significant cost savings and efficiency gains, human curated metadata maintains an edge in quality. The study identifies key challenges including content inaccuracies, hallucinations, and translation issues, suggesting that Large Language Models (LLMs) should serve as complements rather than replacements for human cataloguers. Future work will focus on refining prompts, improving content filtering, and addressing privacy concerns through experimentation with smaller models. This research advances the integration of LLMs in web archiving, offering valuable insights into their current capabilities and outlining directions for future enhancements. The code is available at https://github.com/masamune-prog/warc2summary for further development and use by institutions facing similar challenges.

Tianrui Liu, Changxin Xu, Yuxin Qiao et al.

This paper explores the area of news recommendation, a key component of online information sharing. Initially, we provide a clear introduction to news recommendation, defining the core problem and summarizing current methods and notable recent algorithms. We then present our work on implementing the NRAM (News Recommendation with Attention Mechanism), an attention-based approach for news recommendation, and assess its effectiveness. Our evaluation shows that NRAM has the potential to significantly improve how news content is personalized for users on digital news platforms.

Tianrui Liu, Changxin Xu, Yuxin Qiao et al.

Simultaneous Localization and Mapping (SLAM) presents a formidable challenge in robotics, involving the dynamic construction of a map while concurrently determining the precise location of the robotic agent within an unfamiliar environment. This intricate task is further compounded by the inherent "chicken-and-egg" dilemma, where accurate mapping relies on a dependable estimation of the robot's location, and vice versa. Moreover, the computational intensity of SLAM adds an additional layer of complexity, making it a crucial yet demanding topic in the field. In our research, we address the challenges of SLAM by adopting the Particle Filter SLAM method. Our approach leverages encoded data and fiber optic gyro (FOG) information to enable precise estimation of vehicle motion, while lidar technology contributes to environmental perception by providing detailed insights into surrounding obstacles. The integration of these data streams culminates in the establishment of a Particle Filter SLAM framework, representing a key endeavor in this paper to effectively navigate and overcome the complexities associated with simultaneous localization and mapping in robotic systems.

Tianrui Liu, Qi Cai, Changxin Xu et al.

The wide spread of rumors on social media has caused a negative impact on people's daily life, leading to potential panic, fear, and mental health problems for the public. How to debunk rumors as early as possible remains a challenging problem. Existing studies mainly leverage information propagation structure to detect rumors, while very few works focus on correlation among users that they may coordinate to spread rumors in order to gain large popularity. In this paper, we propose a new detection model, that jointly learns both the representations of user correlation and information propagation to detect rumors on social media. Specifically, we leverage graph neural networks to learn the representations of user correlation from a bipartite graph that describes the correlations between users and source tweets, and the representations of information propagation with a tree structure. Then we combine the learned representations from these two modules to classify the rumors. Since malicious users intend to subvert our model after deployment, we further develop a greedy attack scheme to analyze the cost of three adversarial attacks: graph attack, comment attack, and joint attack. Evaluation results on two public datasets illustrate that the proposed MODEL outperforms the state-of-the-art rumor detection models. We also demonstrate our method performs well for early rumor detection. Moreover, the proposed detection method is more robust to adversarial attacks compared to the best existing method. Importantly, we show that it requires a high cost for attackers to subvert user correlation pattern, demonstrating the importance of considering user correlation for rumor detection.

Ge Luo, Jun-Jie Huang, Qi Yu et al.

Deep Unfolding Network-based methods have emerged as effective solutions for multi-source image fusion by combining model-driven iterative optimization with data-driven deep learning. However, most existing deep unfolding image fusion methods are derived from alternating minimization, which updates the features of different modalities separately. This design introduces considerable computational and memory overhead, limiting deployment on resource-constrained edge devices. To address this issue, we propose CDNet, a lightweight Combined Dictionary Unfolding Network for multi-source image fusion. Rather than introducing a new sparse coding prior or empirically compressing an existing fusion network, CDNet translates the unique-common decomposition prior of coupled dictionary learning into a structurally constrained joint unfolding architecture. The resulting CDBlock follows a block-sparse interaction topology and performs a model-derived joint update of common and modality-specific representations, thereby streamlining feature learning and improving efficiency.In addition, we design a compact High- and Low-frequency Image Fidelity loss for unsupervised training without ground-truth images. We evaluate CDNet on four tasks, including multi-exposure image fusion, infrared and visible image fusion, medical image fusion, and infrared and visible image fusion for semantic segmentation. Experimental results show that CDNet achieves competitive or superior fusion performance with high efficiency. For infrared and visible image fusion, CDNet outperforms competing methods on four of six metrics on the TNO dataset and five of six metrics on the RoadScene dataset. In particular, it surpasses the second-best method by 1.23 dB and 1.59 dB in PSNR on TNO and RoadScene, respectively.

Tianrui Liu, Qi Cai, Changxin Xu et al.

Image captioning strives to generate pertinent captions for specified images, situating itself at the crossroads of Computer Vision (CV) and Natural Language Processing (NLP). This endeavor is of paramount importance with far-reaching applications in recommendation systems, news outlets, social media, and beyond. Particularly within the realm of news reporting, captions are expected to encompass detailed information, such as the identities of celebrities captured in the images. However, much of the existing body of work primarily centers around understanding scenes and actions. In this paper, we explore the realm of image captioning specifically tailored for celebrity photographs, illustrating its broad potential for enhancing news industry practices. This exploration aims to augment automated news content generation, thereby facilitating a more nuanced dissemination of information. Our endeavor shows a broader horizon, enriching the narrative in news reporting through a more intuitive image captioning framework.

Jun-Jie Huang, Tianrui Liu, Zihan Chen et al.

Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8\% of the parameters required by leading methods.

Xihong Yang, Siwei Wang, Jiaqi Jin et al.

Multi-view clustering (MVC) aims to explore the common clustering structure across multiple views. Many existing MVC methods heavily rely on the assumption of view consistency, where alignments for corresponding samples across different views are ordered in advance. However, real-world scenarios often present a challenge as only partial data is consistently aligned across different views, restricting the overall clustering performance. In this work, we consider the model performance decreasing phenomenon caused by data order shift (i.e., from fully to partially aligned) as a generalized multi-view clustering problem. To tackle this problem, we design a causal multi-view clustering network, termed CauMVC. We adopt a causal modeling approach to understand multi-view clustering procedure. To be specific, we formulate the partially aligned data as an intervention and multi-view clustering with partially aligned data as an post-intervention inference. However, obtaining invariant features directly can be challenging. Thus, we design a Variational Auto-Encoder for causal learning by incorporating an encoder from existing information to estimate the invariant features. Moreover, a decoder is designed to perform the post-intervention inference. Lastly, we design a contrastive regularizer to capture sample correlations. To the best of our knowledge, this paper is the first work to deal generalized multi-view clustering via causal learning. Empirical experiments on both fully and partially aligned data illustrate the strong generalization and effectiveness of CauMVC.

Jun-Jie Huang, Zihan Chen, Tianrui Liu et al.

Existing image steganography methods face fundamental limitations in hiding capacity (typically $1\sim7$ images) due to severe information interference and uncoordinated capacity-distortion trade-off. We propose SMILENet, a novel synergistic framework that achieves 25 image hiding through three key innovations: (i) A synergistic network architecture coordinates reversible and non-reversible operations to efficiently exploit information redundancy in both secret and cover images. The reversible Invertible Cover-Driven Mosaic (ICDM) module and Invertible Mosaic Secret Embedding (IMSE) module establish cover-guided mosaic transformations and representation embedding with mathematically guaranteed invertibility for distortion-free embedding. The non-reversible Secret Information Selection (SIS) module and Secret Detail Enhancement (SDE) module implement learnable feature modulation for critical information selection and enhancement. (ii) A unified training strategy that coordinates complementary modules to achieve 3.0x higher capacity than existing methods with superior visual quality. (iii) Last but not least, we introduce a new metric to model Capacity-Distortion Trade-off for evaluating the image steganography algorithms that jointly considers hiding capacity and distortion, and provides a unified evaluation approach for accessing results with different number of secret image. Extensive experiments on DIV2K, Paris StreetView and ImageNet1K show that SMILENet outperforms state-of-the-art methods in terms of hiding capacity, recovery quality as well as security against steganalysis methods.

Changqing Zhou, Zhipeng Luo, Yueru Luo et al.

In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in the current search point cloud given a template point cloud. Motivated by the success of transformers, we propose Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations. PTTR consists of three novel designs. 1) Instead of random sampling, we design Relation-Aware Sampling to preserve relevant points to given templates during subsampling. 2) Furthermore, we propose a Point Relation Transformer (PRT) consisting of a self-attention and a cross-attention module. The global self-attention operation captures long-range dependencies to enhance encoded point features for the search area and the template, respectively. Subsequently, we generate the coarse tracking results by matching the two sets of point features via cross-attention. 3) Based on the coarse tracking results, we employ a novel Prediction Refinement Module to obtain the final refined prediction. In addition, we create a large-scale point cloud single object tracking benchmark based on the Waymo Open Dataset. Extensive experiments show that PTTR achieves superior point cloud tracking in both accuracy and efficiency.

Samuel Budd, Matthew Sinclair, Thomas Day et al.

Fetal ultrasound screening during pregnancy plays a vital role in the early detection of fetal malformations which have potential long-term health impacts. The level of skill required to diagnose such malformations from live ultrasound during examination is high and resources for screening are often limited. We present an interpretable, atlas-learning segmentation method for automatic diagnosis of Hypo-plastic Left Heart Syndrome (HLHS) from a single `4 Chamber Heart' view image. We propose to extend the recently introduced Image-and-Spatial Transformer Networks (Atlas-ISTN) into a framework that enables sensitising atlas generation to disease. In this framework we can jointly learn image segmentation, registration, atlas construction and disease prediction while providing a maximum level of clinical interpretability compared to direct image classification methods. As a result our segmentation allows diagnoses competitive with expert-derived manual diagnosis and yields an AUC-ROC of 0.978 (1043 cases for training, 260 for validation and 325 for testing).

Tianrui Liu, Qingjie Meng, Jun-Jie Huang et al.

Intelligent video summarization algorithms allow to quickly convey the most relevant information in videos through the identification of the most essential and explanatory content while removing redundant video frames. In this paper, we introduce the 3DST-UNet-RL framework for video summarization. A 3D spatio-temporal U-Net is used to efficiently encode spatio-temporal information of the input videos for downstream reinforcement learning (RL). An RL agent learns from spatio-temporal latent scores and predicts actions for keeping or rejecting a video frame in a video summary. We investigate if real/inflated 3D spatio-temporal CNN features are better suited to learn representations from videos than commonly used 2D image features. Our framework can operate in both, a fully unsupervised mode and a supervised training mode. We analyse the impact of prescribed summary lengths and show experimental evidence for the effectiveness of 3DST-UNet-RL on two commonly used general video summarization benchmarks. We also applied our method on a medical video summarization task. The proposed video summarization method has the potential to save storage costs of ultrasound screening videos as well as to increase efficiency when browsing patient video data during retrospective analysis or audit without loosing essential information

Simin Liu, Tianrui Liu, Ali Vakilian et al.

We consider sketching algorithms which first quickly compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g., low rank approximation. In the learning-based sketching paradigm proposed by Indyk et al. [2019], the sketch matrix is found by choosing a random sparse matrix, e.g., the CountSketch, and then updating the values of the non-zero entries by running gradient descent on a training data set. Despite the growing body of work on this paradigm, a noticeable omission is that the locations of the non-zero entries of previous algorithms were fixed, and only their values were learned. In this work we propose the first learning algorithm that also optimizes the locations of the non-zero entries. We show this algorithm gives better accuracy for low rank approximation than previous work, and apply it to other problems such as $k$-means clustering for the first time. We show that our algorithm is provably better in the spiked covariance model and for Zipfian matrices. We also show the importance of the sketch monotonicity property for combining learned sketches. Our empirical results show the importance of optimizing not only the values of the non-zero entries but also their positions.

Tianrui Liu, Qingjie Meng, Athanasios Vlontzos et al.

Video is an essential imaging modality for diagnostics, e.g. in ultrasound imaging, for endoscopy, or movement assessment. However, video hasn't received a lot of attention in the medical image analysis community. In the clinical practice, it is challenging to utilise raw diagnostic video data efficiently as video data takes a long time to process, annotate or audit. In this paper we introduce a novel, fully automatic video summarization method that is tailored to the needs of medical video data. Our approach is framed as reinforcement learning problem and produces agents focusing on the preservation of important diagnostic information. We evaluate our method on videos from fetal ultrasound screening, where commonly only a small amount of the recorded data is used diagnostically. We show that our method is superior to alternative video summarization methods and that it preserves essential information required by clinical diagnostic standards.

Tianrui Liu, Wenhan Luo, Lin Ma et al.

Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, detecting small-scaled pedestrians and occluded pedestrians remains a challenging problem. In this paper, we propose a pedestrian detection method with a couple-network to simultaneously address these two issues. One of the sub-networks, the gated multi-layer feature extraction sub-network, aims to adaptively generate discriminative features for pedestrian candidates in order to robustly detect pedestrians with large variations on scales. The second sub-network targets in handling the occlusion problem of pedestrian detection by using deformable regional RoI-pooling. We investigate two different gate units for the gated sub-network, namely, the channel-wise gate unit and the spatio-wise gate unit, which can enhance the representation ability of the regional convolutional features among the channel dimensions or across the spatial domain, repetitively. Ablation studies have validated the effectiveness of both the proposed gated multi-layer feature extraction sub-network and the deformable occlusion handling sub-network. With the coupled framework, our proposed pedestrian detector achieves state-of-the-art results on the Caltech and the CityPersons pedestrian detection benchmarks.

Tianrui Liu, Jun-Jie Huang, Tianhong Dai et al.

Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, robustly detecting pedestrians with a large variant on sizes and with occlusions remains a challenging problem. In this paper, we propose a gated multi-layer convolutional feature extraction method which can adaptively generate discriminative features for candidate pedestrian regions. The proposed gated feature extraction framework consists of squeeze units, gate units and a concatenation layer which perform feature dimension squeezing, feature elements manipulation and convolutional features combination from multiple CNN layers, respectively. We proposed two different gate models which can manipulate the regional feature maps in a channel-wise selection manner and a spatial-wise selection manner, respectively. Experiments on the challenging CityPersons dataset demonstrate the effectiveness of the proposed method, especially on detecting those small-size and occluded pedestrians.

Tianrui Liu, Mohamed Elmikaty, Tania Stathaki

Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection owing to the strong representation ability of the CNN features. Recently, aggregating features from multiple layers of a CNN has been considered as an effective approach, however, the same approach regarding feature representation is used for detecting pedestrians of varying scales. Consequently, it is not guaranteed that the feature representation for pedestrians of a particular scale is optimised. In this paper, we propose a Scale-Aware Multi-resolution (SAM) method for pedestrian detection which can adaptively select multi-resolution convolutional features according to pedestrian sizes. The proposed SAM method extracts the appropriate CNN features that have strong representation ability as well as sufficient feature resolution, given the size of the pedestrian candidate output from a region proposal network. Moreover, we propose an enhanced SAM method, termed as SAM+, which incorporates complementary features channels and achieves further performance improvement. Evaluations on the challenging Caltech and KITTI pedestrian benchmarks demonstrate the superiority of our proposed method.