Recent advances in LiDAR 3D detection have demonstrated the effectiveness of Transformer-based frameworks in capturing the global dependencies from point cloud spaces, which serialize the 3D voxels into the flattened 1D sequence for iterative self-attention. However, the spatial structure of 3D voxels will be inevitably destroyed during the serialization process. Besides, due to the considerable number of 3D voxels and quadratic complexity of Transformers, multiple sequences are grouped before feeding to Transformers, leading to a limited receptive field. Inspired by the impressive performance of State Space Models (SSM), in this paper, we propose a novel Unified Mamba (UniMamba), which seamlessly integrates the merits of 3D convolution and SSM in a concise multi-head manner, aiming to perform "local and global" spatial context aggregation efficiently and simultaneously. Specifically, a Uni-Mamba block is designed which mainly consists of spatial locality modeling, complementary Z-order serialization and local-global sequential aggregator. The spatial locality modeling module integrates 3D submanifold convolution to capture the dynamic spatial position embedding before serialization. Then the efficient Z-order curve is adopted for serialization both horizontally and vertically. Furthermore, the local-global sequential aggregator adopts the channel grouping strategy to efficiently encode both "local and global" spatial inter-dependencies using multi-head SSM. Additionally, an encoder-decoder architecture with stacked UniMamba blocks is formed to facilitate multi-scale spatial learning hierarchically. Extensive experiments are conducted on three popular datasets: nuScenes, Waymo and Argoverse 2. Particularly, our UniMamba achieves 70.2 mAP on the nuScenes dataset.

Reliable embodied perception from an egocentric perspective is challenging yet essential for autonomous navigation technology of intelligent mobile agents. With the growing demand of social robotics, near-field scene understanding becomes an important research topic in the areas of egocentric perceptual tasks related to navigation in both crowded and unstructured environments. Due to the complexity of environmental conditions and difficulty of surrounding obstacles owing to truncation and occlusion, the perception capability under this circumstance is still inferior. To further enhance the intelligence of mobile robots, in this paper, we setup an egocentric multi-sensor data collection platform based on 3 main types of sensors (Camera, LiDAR and Fisheye), which supports flexible sensor configurations to enable dynamic sight of view from ego-perspective, capturing either near or farther areas. Meanwhile, a large-scale multimodal dataset is constructed, named RoboSense, to facilitate egocentric robot perception. Specifically, RoboSense contains more than 133K synchronized data with 1.4M 3D bounding box and IDs annotated in the full 360° view, forming 216K trajectories across 7.6K temporal sequences. It has 270× and 18× as many annotations of surrounding obstacles within near ranges as the previous datasets collected for autonomous driving scenarios such as KITTI and nuScenes. Moreover, we define a novel matching criterion for near-field 3D perception and prediction metrics. Based on RoboSense, we formulate 6 popular tasks to facilitate the future research development, where the detailed analysis as well as benchmarks are also provided accordingly. Data desensitization measures have been conducted for privacy protection.

Recent advancements in generative models offer promising solutions for synthesizing realistic driving videos, aiding in training autonomous driving perception models. However, existing methods often struggle with high-resolution multi-view generation, mainly due to the significant memory and computational overhead caused by simultaneously inputting multi-view videos into denoising diffusion models. In this paper, we propose a driving video generation framework based on multi-view feature fusion named DriveScape for multi-view 3D condition-guided video generation. We introduce a Bi-Directional Modulated Transformer (BiMoT) module to encode, fuse and inject multiview features along with various 3D road structures and objects, which enables high-resolution multi-view generation. Consequently, our approach allows precise control over video generation, greatly enhancing realism and providing a robust solution for creating high-quality, multi-view driving videos. Our framework achieves state-of-the-art results on the nuScenes dataset, demonstrating impressive generative quality metrics with an FID score of 8.34 and an FVD score of 76.39, as well as superior performance across various perception tasks. This lays the foundation for more accurate environment simulation in autonomous driving. Our project homepage.

Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information for object query decoding, which necessitates explicit supervision from LiDAR points during the training phase. However, the predicted depth quality is still unsatisfactory such as depth discontinuity of object boundaries and indistinction of small objects, which are mainly caused by the sparse supervision of projected points and the use of high-level image features for depth prediction. Besides, cross-view consistency and scale invariance are also overlooked in previous methods. In this paper, we introduce Frequency-aware Positional Depth Embedding (FreqPDE) to equip 2D image features with spatial information for 3D detection transformer decoder, which can be obtained through three main modules. Specifically, the Frequency-aware Spatial Pyramid Encoder (FSPE) constructs a feature pyramid by combining high-frequency edge clues and low-frequency semantics from different levels respectively. Then the Cross-view Scale-invariant Depth Predictor (CSDP) estimates the pixel-level depth distribution with cross-view and efficient channel attention mechanism. Finally, the Positional Depth Encoder (PDE) combines the 2D image features and 3D position embeddings to generate the 3D depth-aware features for query decoding. Additionally, hybrid depth supervision is adopted for complementary depth learning from both metric and distribution aspects. Extensive experiments conducted on the nuScenes dataset demonstrate the effectiveness and superiority of our proposed method.

How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general spatial imagination capability, we present AirScape, the first world model designed for six-degree-of-freedom aerial agents. AirScape predicts future observation sequences based on current visual inputs and motion intentions. Specifically, we construct a dataset for aerial world model training and testing, which consists of 11k video-intention pairs. This dataset includes first-person-view videos capturing diverse drone actions across a wide range of scenarios, with over 1,000 hours spent annotating the corresponding motion intentions. Then we develop a two-phase schedule to train a foundation model-initially devoid of embodied spatial knowledge-into a world model that is controllable by motion intentions and adheres to physical spatio-temporal constraints. Experimental results demonstrate that AirScape significantly outperforms existing foundation models in 3D spatial imagination capabilities, especially with over a 50% improvement in metrics reflecting motion alignment. The project is available at: https://embodiedcity.github.io/AirScape/.

World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current embodied world models exhibit limited physical awareness, particularly in modeling 3D geometry and motion dynamics, resulting in unrealistic video generation for contact-rich robotic scenarios. In this paper, we present RoboScape, a unified physics-informed world model that jointly learns RGB video generation and physics knowledge within an integrated framework. We introduce two key physics-informed joint training tasks: temporal depth prediction that enhances 3D geometric consistency in video rendering, and keypoint dynamics learning that implicitly encodes physical properties (e.g., object shape and material characteristics) while improving complex motion modeling. Extensive experiments demonstrate that RoboScape generates videos with superior visual fidelity and physical plausibility across diverse robotic scenarios. We further validate its practical utility through downstream applications including robotic policy training with generated data and policy evaluation. Our work provides new insights for building efficient physics-informed world models to advance embodied intelligence research. Our code and demos are available at: https://github.com/tsinghua-fib-lab/RoboScape.

Lidar-based 3D Detection is one of the significant components of Autonomous Driving. However, current methods over-focus on improving the performance of 3D Lidar perception, which causes the architecture of networks becoming complicated and hard to deploy. Thus, the methods are difficult to apply in Autonomous Driving for real-time processing. In this paper, we propose a high-efficiency network, SwiftPillars, which includes Swift Pillar Encoder (SPE) and Multi-scale Aggregation Decoder (MAD). The SPE is constructed by a concise Dual-attention Module with lightweight operators. The Dual-attention Module utilizes feature pooling, matrix multiplication, etc. to speed up point-wise and channel-wise attention extraction and fusion. The MAD interconnects multiple scale features extracted by SPE with minimal computational cost to leverage performance. In our experiments, our proposal accomplishes 61.3% NDS and 53.2% mAP in nuScenes dataset. In addition, we evaluate inference time on several platforms (P4, T4, A2, MLU370, RTX3080), where SwiftPillars achieves up to 13.3ms (75FPS) on NVIDIA Tesla T4. Compared with PointPillars, SwiftPillars is on average 26.58% faster in inference speed with equivalent GPUs and a higher mAP of approximately 3.2% in the nuScenes dataset.

Vehicle-to-everything (V2X) is a popular topic in the field of Autonomous Driving in recent years. Vehicle-infrastructure cooperation (VIC) becomes one of the important research area. Due to the complexity of traffic conditions such as blind spots and occlusion, it greatly limits the perception capabilities of single-view roadside sensing sys-tems. To further enhance the accuracy of roadside perception and provide better information to the vehicle side, in this paper, we constructed holographic intersections with various layouts to build a large-scale multi-sensor holo-graphic vehicle-infrastructure cooperation dataset, called HoloVic. Our dataset includes 3 different types of sen-sors (Camera, Lidar; Fisheye) and employs 4 sensor-layouts based on the different intersections. Each intersection is equipped with 6–18 sensors to capture synchronous data. While autonomous vehicles pass through these intersections for collecting VIC data. HoloViccontains in to-talon 100k+ synchronous frames from different sensors. Additionally, we annotated 3D bounding boxes based on Camera, Fisheye, and Lidar: We also associate the IDs of the same objects across different devices and consecutive frames in sequence. Based on HoloVIC, we formulated four tasks to facilitate the development of related research. We also provide benchmarks for these tasks.

Data-driven autonomous driving motion generation tasks are frequently impacted by the limitations of dataset size and the domain gap between datasets, which precludes their extensive application in real-world scenarios. To address this issue, we introduce SMART, a novel autonomous driving motion generation paradigm that models vectorized map and agent trajectory data into discrete sequence tokens. These tokens are then processed through a decoder-only transformer architecture to train for the next token prediction task across spatial-temporal series. This GPT-style method allows the model to learn the motion distribution in real driving scenarios. SMART achieves state-of-the-art performance across most of the metrics on the generative Sim Agents challenge, ranking 1st on the leaderboards of Waymo Open Motion Dataset (WOMD), demonstrating remarkable inference speed. Moreover, SMART represents the generative model in the autonomous driving motion domain, exhibiting zero-shot generalization capabilities: Using only the NuPlan dataset for training and WOMD for validation, SMART achieved a competitive score of 0.72 on the Sim Agents challenge. Lastly, we have collected over 1 billion motion tokens from multiple datasets, validating the model's scalability. These results suggest that SMART has initially emulated two important properties: scalability and zero-shot generalization, and preliminarily meets the needs of large-scale real-time simulation applications. We have released all the code to promote the exploration of models for motion generation in the autonomous driving field. The source code is available at https://github.com/rainmaker22/SMART.

Anomaly detection in surveillance videos is challenging but important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the computational burden and also avoids the negative impact of background noise. However, pose-based methods lack an alternative dynamic representation akin to the explicit motion features, such as optical flow, employed by pixel-based methods. In this paper, a novel Motion Embedder (ME), a label-efficient scheme without extra annotation efforts, is proposed to provide a pose motion representation for the structured posed data from a probability perspective. Furthermore, a novel task-specific Spatial-Temporal Transformer (STT) is deployed for self-supervised pose sequence reconstruction. These two modules are then integrated into a unified framework for pose regularity learning, which is referred to as Motion Prior Regularity Learner (MoPRL). MoPRL achieves competitive results on multiple challenging datasets while minimizing computational costs. Extensive experiments validate the versatility of the proposed modules and provide insights for future research.

Joint detection and tracking, which solves two fundamental vision challenges in a unified manner, is a challenging topic in computer vision. In this area, the proper use of spatial-temporal information in videos can help reduce local defects and improve the quality of feature representations. Although modeling low-level (usually pixel-wise) spatial-temporal information has been studied, instance-level spatial-temporal correlations (i.e., relations between semantic regions in which instances have occurred) have not been fully exploited. In comparison, modeling instance-level correlation is a more flexible and reasonable way to enhance feature representations. However, we have found that conventional instance-level relation learning that works for the separate tasks of detection or tracking is not effective in joint tasks in which a variety of scenarios may be presented. To try to resolve this problem, in this study, we effectively exploited instance-level spatial-temporal semantic information for joint detection and tracking via a joint relation learning pipeline with a novel relation learning mechanism called Similarity- and Quality-Guided Attention (SQGA). Specifically, we added task-specific SQGA relation modules before the corresponding task prediction heads to refine the instance feature representation using features of other reference instances in the neighboring frames; these features are aggregated on the basis of relational affinities. In particular, in SQGA, relational affinities were factorized to similarity and quality terms so that fine-grained supervision rules could be applied. Then we added task-specific attention losses for each SQGA relation module, resulting in a better feature aggregation for the corresponding task. Quantitative experiments based on several challenging multi-object tracking benchmarks showed that our approach was more effective than the baselines and provided competitive results compared with recent state-of-the-art methods.

We present a GAN-based Transformer for general action-conditioned 3D human motion generation, including not only single-person actions but also multi-person interactive actions. Our approach consists of a powerful Action-conditioned motion TransFormer (ActFormer) under a GAN training scheme, equipped with a Gaussian Process latent prior. Such a design combines the strong spatio-temporal representation capacity of Transformer, superiority in generative modeling of GAN, and inherent temporal correlations from the latent prior. Furthermore, ActFormer can be naturally extended to multi-person motions by alternately modeling temporal correlations and human interactions with Transformer encoders. To further facilitate research on multi-person motion generation, we introduce a new synthetic dataset of complex multi-person combat behaviors. Extensive experiments on NTU-13, NTU RGB+D 120, BABEL and the proposed combat dataset show that our method can adapt to various human motion representations and achieve superior performance over the state-of-the-art methods on both single-person and multi-person motion generation tasks, demonstrating a promising step towards a general human motion generator. The project website can be found at https://liangxuy.github.io/actformer/.

In this paper, we take an early step towards video representation learning of human actions with the help of large-scale synthetic videos, particularly for human motion representation enhancement. Specifically, we first introduce an automatic action-related video synthesis pipeline based on a photorealistic video game. A large-scale human action dataset named GATA (GTA Animation Transformed Actions) is then built by the proposed pipeline, which includes 8.1 million action clips spanning over 28K action classes. Based on the presented dataset, we design a contrastive learning framework for human motion representation learning, which shows significant performance improvements on several typical video datasets for action recognition, e.g., Charades, HAA 500 and NTU-RGB. Besides, we further explore a domain adaptation method based on cross-domain positive pairs mining to alleviate the domain gap between synthetic and realistic data. Extensive properties analyses of learned representation are conducted to demonstrate the effectiveness of the proposed dataset for enhancing human motion representation learning.

Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches mainly focus on either of these two difficulties, even though they are closely coupled in cross domain object detection. To solve this problem, we propose a novel Target-perceived Dual-branch Distillation (TDD) framework. By integrating detection branches of both source and target domains in a unified teacher-student learning scheme, it can reduce domain shift and generate reliable supervision effectively. In particular, we first introduce a distinct Target Proposal Perceiver between two domains. It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention. Afterwards, we design a concise Dual Branch Self Distillation strategy for model training, which can progressively integrate complementary object knowledge from different domains via self-distillation in two branches. Finally, we conduct extensive experiments on a number of widely-used scenarios in cross domain object detection. The results show that our TDD significantly outperforms the state-of-the-art methods on all the benchmarks. The codes and models will be released afterwards.

Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from templatesearch pairs and are still unable to track objects with strong variation over a long time span. As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward. We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Specifically, to propagate reliable template feature in the forward propagation process so that the tracker can be trained in the cycle, we first propose a consistency propagation transformation. We then identify an ill-posed penalty problem in conventional cycle training in backward propagation process. Thus, a differentiable region mask is proposed to select features as well as to implicitly penalize tracking errors on intermediate frames. Moreover, since noisy labels may degrade training, we propose a mask-guided loss reweighting strategy to assign dynamic weights based on the quality of pseudo labels. In extensive experiments, our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT. Code is available at https://github.com/FlorinShum/ULAST.

Domain adaptive object detection (DAOD) is a promising way to alleviate performance drop of detectors in new scenes. Albeit great effort made in single source domain adaptation, a more generalized task with multiple source domains remains not being well explored, due to knowledge degradation during their combination. To address this issue, we propose a novel approach, namely target-relevant knowledge preservation (TRKP), to unsupervised multi-source DAOD. Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain. The teacher network is further equipped with an adversarial multi-source disentanglement (AMSD) module to preserve source domain-specific knowledge and simultaneously perform cross-domain alignment. Besides, a holistic target-relevant mining (HTRM) scheme is developed to re-weight the source images according to the source-target relevance. By this means, the teacher network is enforced to capture target-relevant knowledge, thus benefiting decreasing domain shift when mentoring object detection in the target domain. Extensive experiments are conducted on various widely used benchmarks with new state-of-the-art scores reported, highlighting the effectiveness.

Large-scale vehicle trajectories bring great benefits in understanding urban mobility, and can be used to promote a wide range of applications in building intelligent transportation systems. Traditional approaches cannot recover the trajectories of all the vehicles on the roads since they are based on partial trajectory data. To address it, we study the all-vehicle trajectory recovery based on traffic camera video data. However, there are two challenges in this study. First, the quality of the images captured by traffic cameras is unbalanced, so it is hard to identify the same vehicles. Second, the traffic camera observation data are sparse due to the incompleteness of the traffic cameras and possible vehicle miss from the traffic cameras. To deal with these challenges, we design a novel system to recover the vehicle trajectory with the granularity of the road intersection. In this system, we propose an iterative framework to jointly optimize the vehicle re-identification and trajectory recovery tasks. In the vehicle re-identification task, we propose an effective strategy to guide the vehicle clustering based on visual features and the spatio-temporal constraint features updated by the trajectory discovery task. In the trajectory recovery task, we model the spatial and temporal relations as well as the vehicle miss problem by a probabilistic approach to recover the trajectories. Extensive experiments demonstrate that our framework outperforms the existing state-of-art solutions. Finally, our system is deployed in practical applications of SenseTime, China, including traffic congestion analysis and traffic signal control.

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the query and gallery sets, e.g. probe-gallery and gallery-gallery relations, thus hard samples may not be well solved due to the limited or even misleading information. In this paper, we present a novel Context-Aware Graph Convolution Network (CAGCN), where the probe-gallery relations are encoded into the graph nodes and the graph edge connections are well controlled by the gallery-gallery relations. In this way, hard samples can be addressed with the context information flows among other easy samples during the graph reasoning. Specifically, we adopt an effective hard gallery sampler to obtain high recall for positive samples while keeping a reasonable graph size, which can also weaken the imbalanced problem in training process with low computation complexity. Experiments show that the proposed method achieves state-of-the-art performance on both person and vehicle re-identification datasets in a plug and play fashion with limited overhead.

Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations and the inferior quality of confidence scores used for proposal retrieving. In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation. First, we propose a novel boundary regressor based on the complementary characteristics of both starting and ending boundary classifiers. Specifically, we utilize the U-shaped architecture with nested skip connections to capture rich contexts and introduce bi-directional boundary matching mechanism to improve boundary precision. Second, to account for the proposal-proposal relations ignored in previous methods, we devise a proposal relation block to which includes two self-attention modules from the aspects of position and channel. Furthermore, we find that there inevitably exists data imbalanced problems in the positive/negative proposals and temporal durations, which harm the model performance on tail distributions. To relieve this issue, we introduce the scale-balanced re-sampling strategy. Extensive experiments are conducted on two popular benchmarks: ActivityNet-1.3 and THUMOS14, which demonstrate that BSN++ achieves the state-of-the-art performance. Not surprisingly, the proposed BSN++ ranked 1st place in the CVPR19 - ActivityNet challenge leaderboard on temporal action localization task.

Temporal action proposal generation aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet important task in the video understanding field. The proposals generated by current methods still suffer from inaccurate temporal boundaries and inferior confidence used for retrieval owing to the lack of efficient temporal modeling and effective boundary context utilization. In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement. Specifically, we first design a Local-Global Temporal Encoder (LGTE), which adopts the channel grouping strategy to efficiently encode both "local and global" temporal inter-dependencies. Furthermore, both the boundary and internal context of proposals are adopted for frame-level and segment-level boundary regressions, respectively. Temporal Boundary Regressor (TBR) is designed to combine these two regression granularities in an end-to-end fashion, which achieves the precise boundaries and reliable confidence of proposals through progressive refinement. Extensive experiments are conducted on three challenging datasets: HACS, ActivityNet-v1.3, and THUMOS-14, where TCANet can generate proposals with high precision and recall. By combining with the existing action classifier, TCANet can obtain remarkable temporal action detection performance compared with other methods. Not surprisingly, the proposed TCANet won the 1stplace in the CVPR 2020 - HACS challenge leaderboard on temporal action localization task.

Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs. In order to maintain a precise boundary, low-level texture features are directly skip-connected into the deeper layers. Nevertheless, texture features are not only about local structure, but also include global statistical knowledge of the input image. In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STL-Net) for semantic segmentation. For the first time, STL-Net analyzes the distribution of low level information and efficiently utilizes them for the task. Specifically, a novel Quantization and Counting Operator (QCO) is designed to describe the texture information in a statistical manner. Based on QCO, two modules are introduced: (1) Texture Enhance Module (TEM), to capture texture-related information and enhance the texture details; (2) Pyramid Texture Feature Extraction Module (PTFEM), to effectively extract the statistical texture features from multiple scales. Through extensive experiments, we show that the proposed STL-Net achieves state-of-the-art performance on three semantic segmentation benchmarks: Cityscapes, PASCAL Context and ADE20K.

A large-scale system for obtaining fine-grained vehicle trajectories is becoming increasingly important because it lays a solid foundation for a wide range of downstream applications, such as urban traffic optimization, road network profiling, route planning, etc. Traditional methods recover the trajectories from GPS data from apps or coarse-grained traces collected from base stations, which are costly and, more importantly, only cover limited vehicles on the road. Thus, they are not applicable to downstream tasks. To fill this gap, we explore the possibility of recovering vehicle trajectories from the video data recorded by widely deployed traffic cameras. The major challenges lie in the quality of the captured image, low sampling rate, and unbalanced temporal and spatial distribution. To address these challenges, we propose a general system to recover vehicle trajectories at the level of the road intersection, where a novel iterative framework is developed to combine both vehicle clustering and trajectory recovery tasks, which improve their performance simultaneously. The key motivation is that vehicle clustering based on visual features can provide essential discrete points for trajectory recovery, while the recovered routes can introduce spatial-temporal constraints to the initial vehicle clusters for de-noising the false results and complement the missing results. To prove the feasibility of our framework, we collect and plan to release a city-scale traffic camera dataset consisting of 24 hours of videos from 673 cameras across 1,106 intersections. To the best of our knowledge, this benchmark is the first to contain the ground truth of vehicle trajectories with a wide range of spatial and temporal coverage in an urban environment. We conduct extensive experiments and analysis on datasets of different scales to demonstrate the robustness of our framework. Last but not least, we have already deployed the whole system in the business applications of SenseTime, China, including traffic signal control and traffic flow analysis. We highly expect this dataset to further facilitate the research in this field and contribute more to traffic optimization systems in the real world.

Image-based Vehicle ReID methods have suffered from limited information caused by viewpoints, illumination, and occlusion as they usually use a single image as input. Graph convolutional methods (GCN) can alleviate the aforementioned problem by aggregating neighbor samples' information to enhance the feature representation. However, it's uneconomical and computational for the inference processes of GCN-based methods since they need to iterate over all samples for searching the neighbor nodes. In this paper, we propose the first Pseudo-GCN Vehicle ReID method (PGVR) which enables a CNN-based module to performs competitively to GCN-based methods and has a faster and lightweight inference process. To enable the Pseudo-GCN mechanism, a two-branch network and a graph-based knowledge distillation are proposed. The two-branch network consists of a CNN-based student branch and a GCN-based teacher branch. The GCN-based teacher branch adopts a ReID-based GCN to learn the topological optimization ability under the supervision of ReID tasks during training time. Moreover, the graph-based knowledge distillation explicitly transfers the topological optimization ability from the teacher branch to the student branch which acknowledges all nodes. We evaluate our proposed method PGVR on three mainstream Vehicle ReID benchmarks and demonstrate that PGVR achieves state-of-the-art performance.

Convolutional neural networks have gained a remarkable success in computer vision. However, most popular network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained to choose component layers sequentially. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2.35 percent top-1 error rate on CIFAR-10. (2) it offers tremendous reduction of the search space in designing networks, spending only 3 days with 32 GPUs. A faster version can yield a comparable result with only 1 GPU in 20 hours. (3) it has strong generalizability in that the network built on CIFAR also performs well on the larger-scale dataset. The best network achieves very competitive accuracy of 82.0 percent top-1 and 96.0 percent top-5 on ImageNet.

The counting problem aims to estimate the number of objects in images. Due to large scale variation and labeling deviations, it remains a challenging task. The static density map supervised learning framework is widely used in existing methods, which uses the Gaussian kernel to generate a density map as the learning target and utilizes the Euclidean distance to optimize the model. However, the framework is intolerable to the labeling deviations and can not reflect the scale variation. In this paper, we propose an adaptive dilated convolution and a novel supervised learning framework named self-correction (SC) supervision. In the supervision level, the SC supervision utilizes the outputs of the model to iteratively correct the annotations and employs the SC loss to simultaneously optimize the model from both the whole and the individuals. In the feature level, the proposed adaptive dilated convolution predicts a continuous value as the specific dilation rate for each location, which adapts the scale variation better than a discrete and static dilation rate. Extensive experiments illustrate that our approach has achieved a consistent improvement on four challenging benchmarks. Especially, our approach achieves better performance than the state-of-the-art methods on all benchmark datasets.

Neural architecture search (NAS) has demonstrated much success in automatically designing effective neural network architectures. To improve the efficiency of NAS, previous approaches adopt weight sharing method to force all models share the same set of weights. However, it has been observed that a model performing better with shared weights does not necessarily perform better when trained alone. In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the Posterior Fading problem, which compromises the effectiveness of shared weights. To alleviate this problem, we present a novel approach to guide the parameter posterior towards its true distribution. Moreover, a hard latency constraint is introduced during the search so that the desired latency can be achieved. The resulted method, namely Posterior Convergent NAS (PC-NAS), achieves state-of-the-art performance under standard GPU latency constraint on ImageNet.

Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc. Most of previous work only consider the attribute-level feature embedding, which might perform poorly in complicated heterogeneous conditions. To address this problem, we propose a hierarchical feature embedding (HFE) framework, which learns a fine-grained feature embedding by combining attribute and ID information. In HFE, we maintain the inter-class and intra-class feature embedding simultaneously. Not only samples with the same attribute but also samples with the same ID are gathered more closely, which could restrict the feature embedding of visually hard samples with regard to attributes and improve the robustness to variant conditions. We establish this hierarchical structure by utilizing HFE loss consisted of attribute-level and ID-level constraints. We also introduce an absolute boundary regularization and a dynamic loss weight as supplementary components to help build up the feature embedding. Experiments show that our method achieves the state-of-the-art results on two pedestrian attribute datasets and a facial attribute dataset.

In this paper, we propose an inverse reinforcement learning method for architecture search (IRLAS), which trains an agent to learn to search network structures that are topologically inspired by human-designed network. Most existing architecture search approaches totally neglect the topological characteristics of architectures, which results in complicated architecture with a high inference latency. Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt). To avoid raising a too strong prior over the search space, we introduce inverse reinforcement learning to train the mirror stimuli function and exploit it as a heuristic guidance for architecture search, easily generalized to different architecture search algorithms. On CIFAR-10, the best architecture searched by our proposed IRLAS achieves 2.60% error rate. For ImageNet mobile setting, our model achieves a state-of-the-art top-1 accuracy 75.28%, while being 2~4x faster than most auto-generated architectures. A fast version of this model achieves 10% faster than MobileNetV2, while maintaining a higher accuracy.

Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. However, Siamese trackers still have accuracy gap compared with state-of-the-art algorithms and they cannot take advantage of feature from deep networks, such as ResNet-50 or deeper. In this work we prove the core reason comes from the lack of strict translation invariance. By comprehensive theoretical analysis and experimental validations, we break this restriction through a simple yet effective spatial aware sampling strategy and successfully train a ResNet-driven Siamese tracker with significant performance gain. Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size. We conduct extensive ablation studies to demonstrate the effectiveness of the proposed tracker, which obtains currently the best results on four large tracking benchmarks, including OTB2015, VOT2018, UAV123, and LaSOT. Our model will be released to facilitate further studies based on this problem.

Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose a STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in the ResNet architecture with STM blcoks to form a simple yet effective STM network by introducing very limited extra computation cost. Extensive experiments demonstrate that the proposed STM network outperforms the state-of-the-art methods on both temporal-related datasets (i.e., Something-Something v1 & v2 and Jester) and scene-related datasets (i.e., Kinetics-400, UCF-101, and HMDB-51) with the help of encoding spatiotemporal and motion features together.

Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to explore the large design space, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Loss Function Search (AM-LFS) which leverages REINFORCE to search loss functions during the training process. The key contribution of this work is the design of search space which can guarantee the generalization and transferability on different vision tasks by including a bunch of existing prevailing loss functions in a unified formulation. We also propose an efficient optimization framework which can dynamically optimize the parameters of loss function's distribution during training. Extensive experimental results on four benchmark datasets show that, without any tricks, our method outperforms existing hand-crafted loss functions in various computer vision tasks.

Data augmentation is critical to the success of modern deep learning techniques. In this paper, we propose Online Hyper-parameter Learning for Auto-Augmentation (OHL-Auto-Aug), an economical solution that learns the augmentation policy distribution along with network training. Unlike previous methods on auto-augmentation that search augmentation strategies in an offline manner, our method formulates the augmentation policy as a parameterized probability distribution, thus allowing its parameters to be optimized jointly with network parameters. Our proposed OHL-Auto-Aug eliminates the need of re-training and dramatically reduces the cost of the overall search process, while establishes significantly accuracy improvements over baseline models. On both CIFAR-10 and ImageNet, our method achieves remarkable on search accuracy, 60x faster on CIFAR-10 and 24x faster on ImageNet, while maintaining competitive accuracies.

Human attribute analysis is a challenging task in the field of computer vision. One of the significant difficulties is brought from largely imbalance-distributed data. Conventional techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system. To address this problem, we propose a unified framework called Dynamic Curriculum Learning (DCL) to adaptively adjust the sampling strategy and loss weight in each batch, which results in better ability of generalization and discrimination. Inspired by curriculum learning, DCL consists of two-level curriculum schedulers: (1) sampling scheduler which manages the data distribution not only from imbalance to balance but also from easy to hard; (2) loss scheduler which controls the learning importance between classification and metric learning loss. With these two schedulers, we achieve state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.

Video anomaly detection is a challenging problem due to the ambiguity and complexity of how anomalies are defined. Recent approaches for this task mainly utilize deep reconstruction methods and deep prediction ones, but their performances suffer when they cannot guarantee either higher reconstruction errors for abnormal events or lower prediction errors for normal events. Inspired by the predictive coding mechanism explaining how brains detect events violating regularities, we address the Anomaly detection problem with a novel deep Predictive Coding Network, termed as AnoPCN, which consists of a Predictive Coding Module (PCM) and an Error Refinement Module (ERM). Specifically, PCM is designed as a convolutional recurrent neural network with feedback connections carrying frame predictions and feedforward connections carrying prediction errors. By using motion information explicitly, PCM yields better prediction results. To further solve the problem of narrow regularity score gaps in deep reconstruction methods, we decompose reconstruction into prediction and refinement, introducing ERM to reconstruct current prediction error and refine the coarse prediction. AnoPCN unifies reconstruction and prediction methods in an end-to-end framework, and it achieves state-of-the-art performance with better prediction results and larger regularity score gaps on three benchmark datasets including ShanghaiTech Campus, CUHK Avenue, and UCSD Ped2.

Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks. However, most of these trackers can hardly get top performance with real-time speed. In this paper, we propose the Siamese region proposal network (Siamese-RPN) which is end-to-end trained off-line with large-scale image pairs. Specifically, it consists of Siamese subnetwork for feature extraction and region proposal subnetwork including the classification branch and regression branch. In the inference phase, the proposed framework is formulated as a local one-shot detection task. We can pre-compute the template branch of the Siamese subnetwork and formulate the correlation layers as trivial convolution layers to perform online tracking. Benefit from the proposal refinement, traditional multi-scale test and online fine-tuning can be discarded. The Siamese-RPN runs at 160 FPS while achieving leading performance in VOT2015, VOT2016 and VOT2017 real-time challenges.

Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained sequentially to choose component layers. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it performs competitive results in comparison to the hand-crafted state-of-the-art networks on image classification, additionally, the best network generated by BlockQNN achieves 3.54% top-1 error rate on CIFAR-10 which beats all existing auto-generate networks. (2) in the meanwhile, it offers tremendous reduction of the search space in designing networks which only spends 3 days with 32 GPUs, and (3) moreover, it has strong generalizability that the network built on CIFAR also performs well on a larger-scale ImageNet dataset.

Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers only consider appearance features of current frame, and hardly benefit from motion and inter-frame information. The lack of temporal information degrades the tracking performance during challenges such as partial occlusion and deformation. In this paper, we propose the FlowTrack, which focuses on making use of the rich flow information in consecutive frames to improve the feature representation and the tracking accuracy. The FlowTrack formulates individual components, including optical flow estimation, feature extraction, aggregation and correlation filters tracking as special layers in network. To the best of our knowledge, this is the first work to jointly train flow and tracking task in deep learning framework. Then the historical feature maps at predefined intervals are warped and aggregated with current ones by the guiding of flow. For adaptive aggregation, we propose a novel spatial-temporal attention mechanism. In experiments, the proposed method achieves leading performance on OTB2013, OTB2015, VOT2015 and VOT2016.

Convolutional Neural Networks(CNNs) are both computation and memory inten-sive which hindered their deployment in mobile devices. Inspired by the relevantconcept in neural science literature, we propose Synaptic Pruning: a data-drivenmethod to prune connections between input and output feature maps with a newlyproposed class of parameters called Synaptic Strength. Synaptic Strength is de-signed to capture the importance of a connection based on the amount of informa-tion it transports. Experiment results show the effectiveness of our approach. OnCIFAR-10, we prune connections for various CNN models with up to96%, whichresults in significant size reduction and computation saving. Further evaluation onImageNet demonstrates that synaptic pruning is able to discover efficient modelswhich is competitive to state-of-the-art compact CNNs such as MobileNet-V2andNasNet-Mobile. Our contribution is summarized as following: (1) We introduceSynaptic Strength, a new class of parameters for CNNs to indicate the importanceof each connections. (2) Our approach can prune various CNNs with high com-pression without compromising accuracy. (3) Further investigation shows, theproposed Synaptic Strength is a better indicator for kernel pruning compared withthe previous approach in both empirical result and theoretical analysis.