Jianmin Li

Gang Zhang, Ziyi Li, Chufeng Tang et al. · tsinghua

Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and then fuse these features using a lightweight module (e.g., the fusion module in FPN and BiFPN, two typical object detection methods). However, as these methods allocate most computational resources to the classification backbone, the multi-scale feature fusion in these methods is delayed, which may lead to inadequate feature fusion. While some methods perform feature fusion from early stages, they either fail to fully leverage high-level features to guide low-level feature learning or have complex structures, resulting in sub-optimal performance. We propose a streamlined cascade encoder-decoder network, dubbed CEDNet, tailored for dense \mbox{prediction} tasks. All stages in CEDNet share the same encoder-decoder structure and perform multi-scale feature fusion within the decoder. A hallmark of CEDNet is its ability to incorporate high-level features from early stages to guide low-level feature learning in subsequent stages, thereby enhancing the effectiveness of multi-scale feature fusion. We explored three well-known encoder-decoder structures: Hourglass, UNet, and FPN. When integrated into CEDNet, they performed much better than traditional methods that use a pre-designed classification backbone combined with a lightweight fusion module. Extensive experiments on object detection, instance segmentation, and semantic segmentation demonstrated the effectiveness of our method. The code is available at https://github.com/zhanggang001/CEDNet.

Xiaopei Zhu, Zhanhao Hu, Siyuan Huang et al. · tsinghua

Thermal infrared imaging is widely used in body temperature measurement, security monitoring, and so on, but its safety research attracted attention only in recent years. We proposed the infrared adversarial clothing, which could fool infrared pedestrian detectors at different angles. We simulated the process from cloth to clothing in the digital world and then designed the adversarial "QR code" pattern. The core of our method is to design a basic pattern that can be expanded periodically, and make the pattern after random cropping and deformation still have an adversarial effect, then we can process the flat cloth with an adversarial pattern into any 3D clothes. The results showed that the optimized "QR code" pattern lowered the Average Precision (AP) of YOLOv3 by 87.7%, while the random "QR code" pattern and blank pattern lowered the AP of YOLOv3 by 57.9% and 30.1%, respectively, in the digital world. We then manufactured an adversarial shirt with a new material: aerogel. Physical-world experiments showed that the adversarial "QR code" pattern clothing lowered the AP of YOLOv3 by 64.6%, while the random "QR code" pattern clothing and fully heat-insulated clothing lowered the AP of YOLOv3 by 28.3% and 22.8%, respectively. We used the model ensemble technique to improve the attack transferability to unseen models.

Gang Zhang, Junnan Chen, Guohuan Gao et al.

3D object detection in point clouds is important for autonomous driving systems. A primary challenge in 3D object detection stems from the sparse distribution of points within the 3D scene. Existing high-performance methods typically employ 3D sparse convolutional neural networks with small kernels to extract features. To reduce computational costs, these methods resort to submanifold sparse convolutions, which prevent the information exchange among spatially disconnected features. Some recent approaches have attempted to address this problem by introducing large-kernel convolutions or self-attention mechanisms, but they either achieve limited accuracy improvements or incur excessive computational costs. We propose HEDNet, a hierarchical encoder-decoder network for 3D object detection, which leverages encoder-decoder blocks to capture long-range dependencies among features in the spatial space, particularly for large and distant objects. We conducted extensive experiments on the Waymo Open and nuScenes datasets. HEDNet achieved superior detection accuracy on both datasets than previous state-of-the-art methods with competitive efficiency. The code is available at https://github.com/zhanggang001/HEDNet.

Jianhui Li, Jianmin Li, Haoji Zhang et al.

We study the 3D-aware image attribute editing problem in this paper, which has wide applications in practice. Recent methods solved the problem by training a shared encoder to map images into a 3D generator's latent space or by per-image latent code optimization and then edited images in the latent space. Despite their promising results near the input view, they still suffer from the 3D inconsistency of produced images at large camera poses and imprecise image attribute editing, like affecting unspecified attributes during editing. For more efficient image inversion, we train a shared encoder for all images. To alleviate 3D inconsistency at large camera poses, we propose two novel methods, an alternating training scheme and a multi-view identity loss, to maintain 3D consistency and subject identity. As for imprecise image editing, we attribute the problem to the gap between the latent space of real images and that of generated images. We compare the latent space and inversion manifold of GAN models and demonstrate that editing in the inversion manifold can achieve better results in both quantitative and qualitative evaluations. Extensive experiments show that our method produces more 3D consistent images and achieves more precise image editing than previous work. Source code and pretrained models can be found on our project page: https://mybabyyh.github.io/Preim3D/

Daichi Zhang, Zihao Xiao, Shikun Li et al.

Face Forgery videos have elicited critical social public concerns and various detectors have been proposed. However, fully-supervised detectors may lead to easily overfitting to specific forgery methods or videos, and existing self-supervised detectors are strict on auxiliary tasks, such as requiring audio or multi-modalities, leading to limited generalization and robustness. In this paper, we examine whether we can address this issue by leveraging visual-only real face videos. To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervised manner, which is inspired by the observation that fake videos struggle to maintain the natural spatiotemporal consistency even under unknown forgery methods and different perturbations. Our NACO first extracts spatial features of each frame by CNNs then integrates them into Transformer to learn the long-range spatiotemporal representation, leveraging the advantages of CNNs and Transformer on local spatial receptive field and long-term memory respectively. Furthermore, a Spatial Predictive Module~(SPM) and a Temporal Contrastive Module~(TCM) are introduced to enhance the natural consistency representation learning. The SPM aims to predict random masked spatial features from spatiotemporal representation, and the TCM regularizes the latent distance of spatiotemporal representation by shuffling the natural order to disturb the consistency, which could both force our NACO more sensitive to the natural spatiotemporal consistency. After the representation learning stage, a MLP head is fine-tuned to perform the usual forgery video classification task. Extensive experiments show that our method outperforms other state-of-the-art competitors with impressive generalization and robustness.

Jianhui Li, Shilong Liu, Zidong Liu et al.

With the success of Neural Radiance Field (NeRF) in 3D-aware portrait editing, a variety of works have achieved promising results regarding both quality and 3D consistency. However, these methods heavily rely on per-prompt optimization when handling natural language as editing instructions. Due to the lack of labeled human face 3D datasets and effective architectures, the area of human-instructed 3D-aware editing for open-world portraits in an end-to-end manner remains under-explored. To solve this problem, we propose an end-to-end diffusion-based framework termed InstructPix2NeRF, which enables instructed 3D-aware portrait editing from a single open-world image with human instructions. At its core lies a conditional latent 3D diffusion process that lifts 2D editing to 3D space by learning the correlation between the paired images' difference and the instructions via triplet data. With the help of our proposed token position randomization strategy, we could even achieve multi-semantic editing through one single pass with the portrait identity well-preserved. Besides, we further propose an identity consistency module that directly modulates the extracted identity signals into our diffusion process, which increases the multi-view 3D identity consistency. Extensive experiments verify the effectiveness of our method and show its superiority against strong baselines quantitatively and qualitatively. Source code and pre-trained models can be found on our project page: \url{https://mybabyyh.github.io/InstructPix2NeRF}.

Gang Zhang, Junnan Chen, Guohuan Gao et al.

LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However, the computational costs introduced by the dense feature maps grow quadratically as the perception range increases, making these models hard to scale up to long-range detection. Some recent works have attempted to construct fully sparse detectors to solve this issue; nevertheless, the resulting models either rely on a complex multi-stage pipeline or exhibit inferior performance. In this work, we propose SAFDNet, a straightforward yet highly effective architecture, tailored for fully sparse 3D object detection. In SAFDNet, an adaptive feature diffusion strategy is designed to address the center feature missing problem. We conducted extensive experiments on Waymo Open, nuScenes, and Argoverse2 datasets. SAFDNet performed slightly better than the previous SOTA on the first two datasets but much better on the last dataset, which features long-range detection, verifying the efficacy of SAFDNet in scenarios where long-range detection is required. Notably, on Argoverse2, SAFDNet surpassed the previous best hybrid detector HEDNet by 2.6% mAP while being 2.1x faster, and yielded 2.1% mAP gains over the previous best sparse detector FSDv2 while being 1.3x faster. The code will be available at https://github.com/zhanggang001/HEDNet.

Daichi Zhang, Zihao Xiao, Jianmin Li et al.

Face forgery videos have caused severe public concerns, and many detectors have been proposed. However, most of these detectors suffer from limited generalization when detecting videos from unknown distributions, such as from unseen forgery methods. In this paper, we find that different forgery videos have distinct spatiotemporal patterns, which may be the key to generalization. To leverage this finding, we propose a Latent Spatiotemporal Adaptation~(LAST) approach to facilitate generalized face forgery video detection. The key idea is to optimize the detector adaptive to the spatiotemporal patterns of unknown videos in latent space to improve the generalization. Specifically, we first model the spatiotemporal patterns of face videos by incorporating a lightweight CNN to extract local spatial features of each frame and then cascading a vision transformer to learn the long-term spatiotemporal representations in latent space, which should contain more clues than in pixel space. Then by optimizing a transferable linear head to perform the usual forgery detection task on known videos and recover the spatiotemporal clues of unknown target videos in a semi-supervised manner, our detector could flexibly adapt to unknown videos' spatiotemporal patterns, leading to improved generalization. Additionally, to eliminate the influence of specific forgery videos, we pre-train our CNN and transformer only on real videos with two simple yet effective self-supervised tasks: reconstruction and contrastive learning in latent space and keep them frozen during fine-tuning. Extensive experiments on public datasets demonstrate that our approach achieves state-of-the-art performance against other competitors with impressive generalization and robustness.

Ziqi Yuan, Liyuan Wang, Wenbo Ding et al.

In real-world applications, an object detector often encounters object instances from new classes and needs to accommodate them effectively. Previous work formulated this critical problem as incremental object detection (IOD), which assumes the object instances of new classes to be fully annotated in incremental data. However, as supervisory signals are usually rare and expensive, the supervised IOD may not be practical for implementation. In this work, we consider a more realistic setting named semi-supervised IOD (SSIOD), where the object detector needs to learn new classes incrementally from a few labelled data and massive unlabelled data without catastrophic forgetting of old classes. A commonly-used strategy for supervised IOD is to encourage the current model (as a student) to mimic the behavior of the old model (as a teacher), but it generally fails in SSIOD because a dominant number of object instances from old and new classes are coexisting and unlabelled, with the teacher only recognizing a fraction of them. Observing that learning only the classes of interest tends to preclude detection of other classes, we propose to bridge the coexistence of unlabelled classes by constructing two teacher models respectively for old and new classes, and using the concatenation of their predictions to instruct the student. This approach is referred to as DualTeacher, which can serve as a strong baseline for SSIOD with limited resource overhead and no extra hyperparameters. We build various benchmarks for SSIOD and perform extensive experiments to demonstrate the superiority of our approach (e.g., the performance lead is up to 18.28 AP on MS-COCO). Our code is available at \url{https://github.com/chuxiuhong/DualTeacher}.

Gang Zhang, Xin Lu, Jingru Tan et al.

The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature pyramid and the instance-wise pooling process, especially for large objects. In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner. Through fusing more detailed information stage by stage, RefineMask is able to refine high-quality masks consistently. RefineMask succeeds in segmenting hard cases such as bent parts of objects that are over-smoothed by most previous methods and outputs accurate boundaries. Without bells and whistles, RefineMask yields significant gains of 2.6, 3.4, 3.8 AP over Mask R-CNN on COCO, LVIS, and Cityscapes benchmarks respectively at a small amount of additional computational cost. Furthermore, our single-model result outperforms the winner of the LVIS Challenge 2020 by 1.3 points on the LVIS test-dev set and establishes a new state-of-the-art. Code will be available at https://github.com/zhanggang001/RefineMask.

Jianmin Li, Ying Chang, Su-Kit Tang et al.

Background: Retrieval augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine tuning. However, due to the complex reasoning processes and substantial individual differences involved in traditional Chinese medicine (TCM) clinical diagnosis and treatment, traditional RAG methods often exhibit poor performance in this domain. Objective: To address the limitations of conventional RAG approaches in TCM applications, this study aims to develop an improved RAG framework tailored to the characteristics of TCM reasoning. Methods: We developed TCM-DiffRAG, an innovative RAG framework that integrates knowledge graphs (KG) with chains of thought (CoT). TCM-DiffRAG was evaluated on three distinctive TCM test datasets. Results: The experimental results demonstrated that TCM-DiffRAG achieved significant performance improvements over native LLMs. For example, the qwen-plus model achieved scores of 0.927, 0.361, and 0.038, which were significantly enhanced to 0.952, 0.788, and 0.356 with TCM-DiffRAG. The improvements were even more pronounced for non-Chinese LLMs. Additionally, TCM-DiffRAG outperformed directly supervised fine-tuned (SFT) LLMs and other benchmark RAG methods. Conclusions: TCM-DiffRAG shows that integrating structured TCM knowledge graphs with Chain of Thought based reasoning substantially improves performance in individualized diagnostic tasks. The joint use of universal and personalized knowledge graphs enables effective alignment between general knowledge and clinical reasoning. These results highlight the potential of reasoning-aware RAG frameworks for advancing LLM applications in traditional Chinese medicine.

Yuan Wei, Xiaohan Shan, Jianmin Li

Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large language models (LLMs) with evolutionary optimization to address these MARL-specific challenges. The solution centers on two LLM-generated components: a hybrid reward function that dynamically allocates individual credit through reward decomposition, and an observation enhancement function that augments partial observations with inferred environmental context. An evolutionary algorithm optimizes these components through iterative MARL training cycles, where top-performing candidates guide subsequent LLM generations. Evaluations in Multi-Agent Particle Environments (MPE) demonstrate LERO's superiority over baseline methods, with improved task performance and training efficiency.

Chang Liu, Ying Chang, Jianmin Li et al.

Objectives: Large language models (LLMs) can harness medical knowledge for intelligent question answering (Q&A), promising support for auxiliary diagnosis and medical talent cultivation. However, there is a deficiency of highly efficient retrieval-augmented generation (RAG) frameworks within the domain of Traditional Chinese Medicine (TCM). Our purpose is to observe the effect of the Tree-Organized Self-Reflective Retrieval (TOSRR) framework on LLMs in TCM Q&A tasks. Materials and Methods: We introduce the novel approach of knowledge organization, constructing a tree structure knowledge base with hierarchy. At inference time, our self-reflection framework retrieves from this knowledge base, integrating information across chapters. Questions from the TCM Medical Licensing Examination (MLE) and the college Classics Course Exam (CCE) were randomly selected as benchmark datasets. Results: By coupling with GPT-4, the framework can improve the best performance on the TCM MLE benchmark by 19.85% in absolute accuracy, and improve recall accuracy from 27% to 38% on CCE datasets. In manual evaluation, the framework improves a total of 18.52 points across dimensions of safety, consistency, explainability, compliance, and coherence. Conclusion: The TOSRR framework can effectively improve LLM's capability in Q&A tasks of TCM.

Xiaopei Zhu, Yuqiu Liu, Zhanhao Hu et al.

Infrared physical adversarial examples are of great significance for studying the security of infrared AI systems that are widely used in our lives such as autonomous driving. Previous infrared physical attacks mainly focused on 2D infrared pedestrian detection which may not fully manifest its destructiveness to AI systems. In this work, we propose a physical attack method against infrared detectors based on 3D modeling, which is applied to a real car. The goal is to design a set of infrared adversarial stickers to make cars invisible to infrared detectors at various viewing angles, distances, and scenes. We build a 3D infrared car model with real infrared characteristics and propose an infrared adversarial pattern generation method based on 3D mesh shadow. We propose a 3D control points-based mesh smoothing algorithm and use a set of smoothness loss functions to enhance the smoothness of adversarial meshes and facilitate the sticker implementation. Besides, We designed the aluminum stickers and conducted physical experiments on two real Mercedes-Benz A200L cars. Our adversarial stickers hid the cars from Faster RCNN, an object detector, at various viewing angles, distances, and scenes. The attack success rate (ASR) was 91.49% for real cars. In comparison, the ASRs of random stickers and no sticker were only 6.21% and 0.66%, respectively. In addition, the ASRs of the designed stickers against six unseen object detectors such as YOLOv3 and Deformable DETR were between 73.35%-95.80%, showing good transferability of the attack performance across detectors.

Yufeng Chi, Huimin Ma, Kafeng Wang et al.

While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches typically update 3D representations through iterative refinement based on a single editing view. However, these methods often suffer from slow convergence and blurry artifacts caused by cross-view inconsistencies. Recent methods improve efficiency by propagating 2D editing attention features, yet still exhibit fine-grained inconsistencies and failure modes in complex scenes due to insufficient constraints. To address this, we propose \textbf{DisCo3D}, a novel framework that distills 3D consistency priors into a 2D editor. Our method first fine-tunes a 3D generator using multi-view inputs for scene adaptation, then trains a 2D editor through consistency distillation. The edited multi-view outputs are finally optimized into 3D representations via Gaussian Splatting. Experimental results show DisCo3D achieves stable multi-view consistency and outperforms state-of-the-art methods in editing quality.

Fei Kong, Xiaohan Shan, Yanwei Hu et al.

Neural Architecture Search (NAS) is challenged by the trade-off between search space exploration and efficiency, especially for complex tasks. While recent LLM-based NAS methods have shown promise, they often suffer from static search strategies and ambiguous architecture representations. We propose PhaseNAS, an LLM-based NAS framework with dynamic phase transitions guided by real-time score thresholds and a structured architecture template language for consistent code generation. On the NAS-Bench-Macro benchmark, PhaseNAS consistently discovers architectures with higher accuracy and better rank. For image classification (CIFAR-10/100), PhaseNAS reduces search time by up to 86% while maintaining or improving accuracy. In object detection, it automatically produces YOLOv8 variants with higher mAP and lower resource cost. These results demonstrate that PhaseNAS enables efficient, adaptive, and generalizable NAS across diverse vision tasks.

Zhiyi Huang, Xiaohan Shan, Jianmin Li

Lifelong Reinforcement Learning (LRL) holds significant potential for addressing sequential tasks, but it still faces considerable challenges. A key difficulty lies in effectively preventing catastrophic forgetting and facilitating knowledge transfer while maintaining reliable decision-making performance across subsequent tasks in dynamic environments. To tackle this, we propose a novel framework, SDW (Similarity-Driven Weighting Framework), which leverages large-language-model-generated dynamic functions to precisely control the training process. The core of SDW lies in two functions pre-generated by large models: the task similarity function and the weight computation function. The task similarity function extracts multidimensional features from task descriptions to quantify the similarities and differences between tasks in terms of states, actions, and rewards. The weight computation function dynamically generates critical training parameters based on the similarity information, including the proportion of old task data stored in the Replay Buffer and the strategy consistency weight in the loss function, enabling an adaptive balance between learning new tasks and transferring knowledge from previous tasks. By generating function code offline prior to training, rather than relying on large-model inference during the training process, the SDW framework reduces computational overhead while maintaining efficiency in sequential task scenarios. Experimental results on Atari and MiniHack sequential tasks demonstrate that SDW significantly outperforms existing lifelong reinforcement learning methods.

Yuan Wei, Xiaohan Shan, Ran Miao et al.

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven agent-generates-agent framework for fully automated RL agent design. Agent$^2$ autonomously translates natural language task descriptions and environment code into executable RL solutions without human intervention. The framework adopts a dual-agent architecture: a Generator Agent that analyzes tasks and designs agents, and a Target Agent that is automatically generated and executed. To better support automation, RL development is decomposed into two stages, MDP modeling and algorithmic optimization, facilitating targeted and effective agent generation. Built on the Model Context Protocol, Agent$^2$ provides a unified framework for standardized agent creation across diverse environments and algorithms, incorporating adaptive training management and intelligent feedback analysis for continuous refinement. Extensive experiments on benchmarks including MuJoCo, MetaDrive, MPE, and SMAC show that Agent$^2$ outperforms manually designed baselines across all tasks, achieving up to 55\% performance improvement with consistent average gains. By enabling a closed-loop, end-to-end automation pipeline, this work advances a new paradigm in which agents can design and optimize other agents, underscoring the potential of agent-generates-agent systems for automated AI development.

Weiyi Zhang, Shuning Zhao, Le Liu et al.

In authentication scenarios, applications of practical speaker verification systems usually require a person to read a dynamic authentication text. Previous studies played an audio adversarial example as a digital signal to perform physical attacks, which would be easily rejected by audio replay detection modules. This work shows that by playing our crafted adversarial perturbation as a separate source when the adversary is speaking, the practical speaker verification system will misjudge the adversary as a target speaker. A two-step algorithm is proposed to optimize the universal adversarial perturbation to be text-independent and has little effect on the authentication text recognition. We also estimated room impulse response (RIR) in the algorithm which allowed the perturbation to be effective after being played over the air. In the physical experiment, we achieved targeted attacks with success rate of 100%, while the word error rate (WER) on speech recognition was only increased by 3.55%. And recorded audios could pass replay detection for the live person speaking.

Chufeng Tang, Hang Chen, Xiao Li et al.

Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory. The boundaries of predicted instance masks are usually imprecise due to the low spatial resolution of feature maps and the imbalance problem caused by the extremely low proportion of boundary pixels. To address these issues, we propose a conceptually simple yet effective post-processing refinement framework to improve the boundary quality based on the results of any instance segmentation model, termed BPR. Following the idea of looking closer to segment boundaries better, we extract and refine a series of small boundary patches along the predicted instance boundaries. The refinement is accomplished by a boundary patch refinement network at higher resolution. The proposed BPR framework yields significant improvements over the Mask R-CNN baseline on Cityscapes benchmark, especially on the boundary-aware metrics. Moreover, by applying the BPR framework to the PolyTransform + SegFix baseline, we reached 1st place on the Cityscapes leaderboard.

Xiao Li, Jianmin Li, Ting Dai et al.

Recently, it was found that many real-world examples without intentional modifications can fool machine learning models, and such examples are called "natural adversarial examples". ImageNet-A is a famous dataset of natural adversarial examples. By analyzing this dataset, we hypothesized that large, cluttered and/or unusual background is an important reason why the images in this dataset are difficult to be classified. We validated the hypothesis by reducing the background influence in ImageNet-A examples with object detection techniques. Experiments showed that the object detection models with various classification models as backbones obtained much higher accuracy than their corresponding classification models. A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53.95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A. We then manually cropped the objects in images from ImageNet-A and created a new dataset, named ImageNet-A-Plus. A human test on the new dataset showed that the deep learning-based classifiers still performed quite poorly compared with humans. Therefore, the new dataset can be used to study the robustness of classification models to the internal variance of objects without considering the background disturbance.

Haoran Chen, Jianmin Li, Simone Frintrop et al.

Video captioning automatically generates short descriptions of the video content, usually in form of a single sentence. Many methods have been proposed for solving this task. A large dataset called MSR Video to Text (MSR-VTT) is often used as the benchmark dataset for testing the performance of the methods. However, we found that the human annotations, i.e., the descriptions of video contents in the dataset are quite noisy, e.g., there are many duplicate captions and many captions contain grammatical problems. These problems may pose difficulties to video captioning models for learning underlying patterns. We cleaned the MSR-VTT annotations by removing these problems, then tested several typical video captioning models on the cleaned dataset. Experimental results showed that data cleaning boosted the performances of the models measured by popular quantitative metrics. We recruited subjects to evaluate the results of a model trained on the original and cleaned datasets. The human behavior experiment demonstrated that trained on the cleaned dataset, the model generated captions that were more coherent and more relevant to the contents of the video clips.

Xiaopei Zhu, Xiao Li, Jianmin Li et al.

Thermal infrared detection systems play an important role in many areas such as night security, autonomous driving, and body temperature detection. They have the unique advantages of passive imaging, temperature sensitivity and penetration. But the security of these systems themselves has not been fully explored, which poses risks in applying these systems. We propose a physical attack method with small bulbs on a board against the state of-the-art pedestrian detectors. Our goal is to make infrared pedestrian detectors unable to detect real-world pedestrians. Towards this goal, we first showed that it is possible to use two kinds of patches to attack the infrared pedestrian detector based on YOLOv3. The average precision (AP) dropped by 64.12% in the digital world, while a blank board with the same size caused the AP to drop by 29.69% only. After that, we designed and manufactured a physical board and successfully attacked YOLOv3 in the real world. In recorded videos, the physical board caused AP of the target detector to drop by 34.48%, while a blank board with the same size caused the AP to drop by 14.91% only. With the ensemble attack techniques, the designed physical board had good transferability to unseen detectors. We also proposed the first physical multispectral (infrared and visible) attack. By using a combination method, we successfully hide from the visible light and infrared object detection systems at the same time.

Jiajun Zhang, Pengyuan Ren, Jianmin Li

Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios. In most cases, the existence of a particular attribute is strongly related to a partial region. Recent works design complicated modules, e.g., attention mechanism and proposal of body parts to localize the attribute corresponding region. These works further prove that localization of attribute specific regions precisely will help in improving performance. However, these part-information-based methods are still not accurate as well as increasing model complexity which makes it hard to deploy on realistic applications. In this paper, we propose a Deep Template Matching based method to capture body parts features with less computation. Further, we also proposed an auxiliary supervision method that use human pose keypoints to guide the learning toward discriminative local cues. Extensive experiments show that the proposed method outperforms and has lower computational complexity, compared with the state-of-the-art approaches on large-scale pedestrian attribute datasets, including PETA, PA-100K, RAP, and RAPv2 zs.

Haoran Chen, Jianmin Li, Xiaolin Hu

Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some problems in the decoder of a video captioning model. We make a thorough investigation into the decoder and adopt three techniques to improve the performance of the model. First of all, a combination of variational dropout and layer normalization is embedded into a recurrent unit to alleviate the problem of overfitting. Secondly, a new online method is proposed to evaluate the performance of a model on a validation set so as to select the best checkpoint for testing. Finally, a new training strategy called professional learning is proposed which uses the strengths of a captioning model and bypasses its weaknesses. It is demonstrated in the experiments on Microsoft Research Video Description Corpus (MSVD) and MSR-Video to Text (MSR-VTT) datasets that our model has achieved the best results evaluated by BLEU, CIDEr, METEOR and ROUGE-L metrics with significant gains of up to 18% on MSVD and 3.5% on MSR-VTT compared with the previous state-of-the-art models.

Shifeng Zhang, Jianmin Li, Bo Zhang

With the rapid growth of various types of multimodal data, cross-modal deep hashing has received broad attention for solving cross-modal retrieval problems efficiently. Most cross-modal hashing methods follow the traditional supervised hashing framework in which the $O(n^2)$ data pairs and $O(n^3)$ data triplets are generated for training, but the training procedure is less efficient because the complexity is high for large-scale dataset. To address these issues, we propose a novel and efficient cross-modal hashing algorithm in which the unary loss is introduced. First of all, We introduce the Cross-Modal Unary Loss (CMUL) with $O(n)$ complexity to bridge the traditional triplet loss and classification-based unary loss. A more accurate bound of the triplet loss for structured multilabel data is also proposed in CMUL. Second, we propose the novel Joint Cluster Cross-Modal Hashing (JCCH) algorithm for efficient hash learning, in which the CMUL is involved. The resultant hashcodes form several clusters in which the hashcodes in the same cluster share similar semantic information, and the heterogeneity gap on different modalities is diminished by sharing the clusters. The proposed algorithm is able to be applied to various types of data, and experiments on large-scale datasets show that the proposed method is superior over or comparable with state-of-the-art cross-modal hashing methods, and training with the proposed method is more efficient than others.

Shifeng Zhang, Jianmin Li, Bo Zhang

Hashing method maps similar high-dimensional data to binary hashcodes with smaller hamming distance, and it has received broad attention due to its low storage cost and fast retrieval speed. Pairwise similarity is easily obtained and widely used for retrieval, and most supervised hashing algorithms are carefully designed for the pairwise supervisions. As labeling all data pairs is difficult, semi-supervised hashing is proposed which aims at learning efficient codes with limited labeled pairs and abundant unlabeled ones. Existing methods build graphs to capture the structure of dataset, but they are not working well for complex data as the graph is built based on the data representations and determining the representations of complex data is difficult. In this paper, we propose a novel teacher-student semi-supervised hashing framework in which the student is trained with the pairwise information produced by the teacher network. The network follows the smoothness assumption, which achieves consistent distances for similar data pairs so that the retrieval results are similar for neighborhood queries. Experiments on large-scale datasets show that the proposed method reaches impressive gain over the supervised baselines and is superior to state-of-the-art semi-supervised hashing methods.

Pengyuan Ren, Jianmin Li

Person re-identification (ReID) is aimed at identifying the same person across videos captured from different cameras. In the view that networks extracting global features using ordinary network architectures are difficult to extract local features due to their weak attention mechanisms, researchers have proposed a lot of elaborately designed ReID networks, while greatly improving the accuracy, the model size and the feature extraction latency are also soaring. We argue that a relatively compact ordinary network extracting globally pooled features has the capability to extract discriminative local features and can achieve state-of-the-art precision if only the model's parameters are properly learnt. In order to reduce the difficulty in learning hard identity labels, we propose a novel knowledge distillation method: Factorized Distillation, which factorizes both feature maps and retrieval features of holistic ReID network to mimic representations of multiple partial ReID models, thus transferring the knowledge from partial ReID models to the holistic network. Experiments show that the performance of model trained with the proposed method can outperform state-of-the-art with relatively few network parameters.

Yubo Sun, Yuqi Lei, Wulin Zou et al.

Body weight support (BWS) is a fundamental technique in rehabilitation. Along with the dramatic progressing of rehabilitation science and engineering, BWS is quickly evolving with new initiatives and has attracted deep research effort in recent years. We have built up a novel gravity offloading system, in which the patient is allowed to move freely in the three-dimensional Cartesian space and receives support against gravity. Thus, the patients, especially for those that suffer from neurological injury such as stroke or spinal cord injury, can focus their residual motor control capabilities on essential therapeutic trainings of balance and gait. The real-time force control performance is critical for the BWS unit to provide suitable support and avoid disturbance. In this work, we have re-designed our BWS unit with a series elastic actuation structure to improve the human-robot interaction performance. Further, the 2 degrees of freedom (2-DOF) control approach was taken for accurate and robust BWS force control. Both simulation and experimental results have validated the efficacy of the BWS design and real-time control methods.

Shifeng Zhang, Jianmin Li, Bo Zhang

Hashing method maps similar data to binary hashcodes with smaller hamming distance, which has received a broad attention due to its low storage cost and fast retrieval speed. With the rapid development of deep learning, deep hashing methods have achieved promising results in efficient information retrieval. Most of the existing deep hashing methods adopt pairwise or triplet losses to deal with similarities underlying the data, but the training is difficult and less efficient because $O(n^2)$ data pairs and $O(n^3)$ triplets are involved. To address these issues, we propose a novel deep hashing algorithm with unary loss which can be trained very efficiently. We first of all introduce a Unary Upper Bound of the traditional triplet loss, thus reducing the complexity to $O(n)$ and bridging the classification-based unary loss and the triplet loss. Second, we propose a novel Semantic Cluster Deep Hashing (SCDH) algorithm by introducing a modified Unary Upper Bound loss, named Semantic Cluster Unary Loss (SCUL). The resultant hashcodes form several compact clusters, which means hashcodes in the same cluster have similar semantic information. We also demonstrate that the proposed SCDH is easy to be extended to semi-supervised settings by incorporating the state-of-the-art semi-supervised learning algorithms. Experiments on large-scale datasets show that the proposed method is superior to state-of-the-art hashing algorithms.

Shifeng Zhang, Jianmin Li, Jinma Guo et al.

Hashing method maps similar data to binary hashcodes with smaller hamming distance, and it has received a broad attention due to its low storage cost and fast retrieval speed. However, the existing limitations make the present algorithms difficult to deal with large-scale datasets: (1) discrete constraints are involved in the learning of the hash function; (2) pairwise or triplet similarity is adopted to generate efficient hashcodes, resulting both time and space complexity are greater than O(n^2). To address these issues, we propose a novel discrete supervised hash learning framework which can be scalable to large-scale datasets. First, the discrete learning procedure is decomposed into a binary classifier learning scheme and binary codes learning scheme, which makes the learning procedure more efficient. Second, we adopt the Asymmetric Low-rank Matrix Factorization and propose the Fast Clustering-based Batch Coordinate Descent method, such that the time and space complexity is reduced to O(n). The proposed framework also provides a flexible paradigm to incorporate with arbitrary hash function, including deep neural networks and kernel methods. Experiments on large-scale datasets demonstrate that the proposed method is superior or comparable with state-of-the-art hashing algorithms.

Jinma Guo, Jianmin Li

Along with data on the web increasing dramatically, hashing is becoming more and more popular as a method of approximate nearest neighbor search. Previous supervised hashing methods utilized similarity/dissimilarity matrix to get semantic information. But the matrix is not easy to construct for a new dataset. Rather than to reconstruct the matrix, we proposed a straightforward CNN-based hashing method, i.e. binarilizing the activations of a fully connected layer with threshold 0 and taking the binary result as hash codes. This method achieved the best performance on CIFAR-10 and was comparable with the state-of-the-art on MNIST. And our experiments on CIFAR-10 suggested that the signs of activations may carry more information than the relative values of activations between samples, and that the co-adaption between feature extractor and hash functions is important for hashing.