Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays. It has high practical impacts for many applications across robotics, security, healthcare, etc. The two-stage paradigm of Faster R-CNN inspires a standard paradigm of video action detection in object detection, i.e., firstly generating person proposals and then classifying their actions. However, none of the existing solutions could provide fine-grained action detection to the "who-when-where-what" level. This paper presents a tracking-based solution to accurately and efficiently localize predefined key actions spatially (by predicting the associated target IDs and locations) and temporally (by predicting the time in exact frame indices). This solution won first place in the UAV-Video Track of 2021 Low-Power Computer Vision Challenge (LPCVC).
Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）；ByteDance Inc.（字节跳动公司）
Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings cal…
Huazhong University of Science and Technology（华中科技大学）；ByteDance Inc.（字节跳动公司）
Temporal action detection (TAD) is an important yet challenging task in video understanding. It aims to simultaneously predict the semantic label and the temporal interval of every action instance in an untrimmed video. Rather than end-to-end learning, most existing methods adopt a head-only learning paradigm, where the video encoder is pre-trained for action classification, and only the detection head upon the encoder is optimized for TAD. The effect of end-to-end learning is not systematically evaluated. Besides, there lacks an in-depth study on the efficiency-accuracy trade-off in end-to-en…
Leibniz Universität Hannover（莱布尼茨汉诺威大学）；Technische Universität München（慕尼黑工业大学）
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information might be ignored. Consequently, this work demonstrates how to fuse two detectors into a tracking system. To obtain the trajectories, we propose to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program. As such problems are NP-hard, the solution can only be approximated. Based on the Frank-Wolfe algorithm, we present a new solver that is …
We present single-shot multi-object tracker (SMOT), a new tracking framework that converts any single-shot detector (SSD) model into an online multiple object tracker, which emphasizes simultaneously detecting and tracking of the object paths. Contrary to the existing tracking by detection approaches which suffer from errors made by the object detectors, SMOT adopts the recently proposed scheme of tracking by re-detection. We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module. With this design SMOT is able to generate tracklets with a constant per-fra…
Temporal action detection is a fundamental yet challenging task in video understanding. Many of the state-of-the-art methods predict the boundaries of action instances based on predetermined anchors akin to the two-dimensional object detection detectors. However, it is hard to detect all the action instances with predetermined temporal scales because the durations of instances in untrimmed videos can vary from few seconds to several minutes. In this paper, we propose a novel action detection architecture named anchor-free one-stage temporal action detector (AFO-TAD). AFO-TAD achieves better pe…
The University of Sydney（悉尼大学）；ShanghaiTech University（上海科技大学）；National University of Singapore（新加坡国立大学）；Stevens Institute of Technology（史蒂文斯理工学院）
Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is to enhance data association by generating more discriminative identity embeddings. Some works combined both directions within one framework but handled them as two individual tasks, thus gaining little mutual benefits. In this paper, we propose a novel unified model with synergy between position prediction and embedding association. The two tasks are linked …
Universidad Autónoma de Madrid（马德里自治大学）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）
How would you fairly evaluate two multi-object tracking algorithms (i.e. trackers), each one employing a different object detector? Detectors keep improving, thus trackers can make less effort to estimate object states over time. Is it then fair to compare a new tracker employing a new detector with another tracker using an old detector? In this paper, we propose a novel performance measure, named Tracking Effort Measure (TEM), to evaluate trackers that use different detectors. TEM estimates the improvement that the tracker does with respect to its input data (i.e. detections) at frame level (…
University of Western Australia（西澳大利亚大学）；Deakin University（迪肯大学）；University of Central Florida（中佛罗里达大学）
Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection.This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this issue, we introduce Deep Motion Modeling Network (DMM-Net) that can estimate multiple objects' motion parameters to perform joint detection and association in an end-to-end manner. DMM-Net models object features over multiple frames and simultaneously infers object classes, visibility, and their motion parameters. These outputs are readily used to update the tra…
Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking
Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）；CiTIUS, Univ. of Santiago de Compostela（西班牙圣地亚哥-德孔波斯特拉大学CiTIUS研究中心）；Inria Grenoble, Univ. Grenoble Alpes（法国国家信息与自动化研究所格勒诺布尔分部、格勒诺布尔阿尔卑斯大学）
State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to obtain accurate detections due to heavy occlusions and high crowd density. In this paper, we propose a new MOT paradigm, tracking-by-counting, tailored for crowded scenes. Using crowd density maps, we jointly model detection, counting, and tracking of multiple targets as a network flow program, which simultaneously finds the global optimal detections and tr…
This paper presents a robust multi-class multi-object tracking (MCMOT) formulated by a Bayesian filtering framework. Multi-object tracking for unlimited object classes is conducted by combining detection responses and changing point detection (CPD) algorithm. The CPD model is used to observe abrupt or abnormal changes due to a drift and an occlusion based spatiotemporal characteristics of track states. The ensemble of convolutional neural network (CNN) based object detector and Lucas-Kanede Tracker (KLT) based motion detector is employed to compute the likelihoods of foreground regions as the …
Industrial Artificial Intelligence (INARI) Research Lab（工业人工智能（INARI）研究实验室）；Escuela Superior Politecnica del Litoral（滨海高等理工学院）
Multiple-Object Tracking (MOT) is of crucial importance for applications such as retail video analytics and video surveillance. Object detectors are often the computational bottleneck of modern MOT systems, limiting their use for real-time applications. In this paper, we address this issue by leveraging on an ensemble of detectors, each running every f frames. We measured the performance of our system in the MOT16 benchmark. The proposed model surpassed other online entries of the MOT16 challenge in speed, while maintaining an acceptable accuracy.
Efficient tracking algorithms are a crucial part of particle tracking detectors. While a lot of work has been done in designing a plethora of algorithms, these usually require tedious tuning for each use case. (Weakly) supervised Machine Learning-based approaches can leverage the actual raw data for maximal performance. Yet in realistic scenarios, sufficient high-quality labeled data is not available. While training might be performed on simulated data, the reproduction of realistic signal and noise in the detector requires substantial effort, compromising this approach. Here we propose a nove…
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this paper, we propose a unified network for TAD, termed Faster-TAD, by re-purposing a Faster-RCNN like architecture. To tackle the unique difficulty in TAD, we make important improvements over the original framework. We propose a new Context-Adaptive Proposal Module and an innovative Fake-Proposal Generation Block. What's more, we use atomic action features to improv…
Johns Hopkins University（约翰斯·霍普金斯大学）；Hong Kong Baptist University（香港浸会大学）
This paper addresses fully automated multi-person tracking in complex environments with challenging occlusion and extensive pose variations. Our solution combines multiple detectors for a set of different regions of interest (e.g., full-body and head) for multi-person tracking. The use of multiple detectors leads to fewer miss detections as it is able to exploit the complementary strengths of the individual detectors. While the number of false positives may increase with the increased number of bounding boxes detected from multiple detectors, we propose to group the detection outputs by boundi…
Adaptive tracking-by-detection approaches are popular for tracking arbitrary objects. They treat the tracking problem as a classification task and use online learning techniques to update the object model. However, these approaches are heavily invested in the efficiency and effectiveness of their detectors. Evaluating a massive number of samples for each frame (e.g., obtained by a sliding window) forces the detector to trade the accuracy in favor of speed. Furthermore, misclassification of borderline samples in the detector introduce accumulating errors in tracking. In this study, we propose a…
Multiple object tracking (MOT) in urban traffic aims to produce the trajectories of the different road users that move across the field of view with different directions and speeds and that can have varying appearances and sizes. Occlusions and interactions among the different objects are expected and common due to the nature of urban road traffic. In this work, a tracking framework employing classification label information from a deep learning detection approach is used for associating the different objects, in addition to object position and appearances. We want to investigate the performan…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Shanghai Jiao Tong University（上海交通大学）
Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train directly from video frames with extremely low GPU memory consumption. Our main idea is to minimize and balance the heavy computation among features and gradients in each training iteration. We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder. To further al…
Detector-Augmented SAMURAI for Long-Duration Drone Tracking
Institute for the Protection of Terrestrial Infrastructures, German Aerospace Center (DLR)（地面基础设施保护研究所，德国航空航天中心（DLR））；ACIDA Lab, Technical University of Applied Sciences Würzburg-Schweinfurt（应用技术大学施魏尔堡-施维恩富特学院ACIDA实验室）；Data Science Institute, European University of Technology（欧洲技术大学数据科学研究所）；LIST3N, Université de Technologie de Troyes（图卢兹理工大学LIST3N）
Huazhong University of Science and Technology（华中科技大学）；Microsoft Research Asia（微软亚洲研究院）
State-of-the-art object detectors and trackers are developing fast. Trackers are in general more efficient than detectors but bear the risk of drifting. A question is hence raised -- how to improve the accuracy of video object detection/tracking by utilizing the existing detectors and trackers within a given time budget? A baseline is frame skipping -- detecting every N-th frames and tracking for the frames in between. This baseline, however, is suboptimal since the detection frequency should depend on the tracking quality. To this end, we propose a scheduler network, which determines to detec…
We consider the tracking problem as a special type of object detection problem, which we call instance detection. With proper initialization, a detector can be quickly converted into a tracker by learning the new instance from a single image. We find that model-agnostic meta-learning (MAML) offers a strategy to initialize the detector that satisfies our needs. We propose a principled three-step approach to build a high-performance tracker. First, pick any modern object detector trained with gradient descent. Second, conduct offline training (or initialization) with MAML. Third, perform domain …
University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Baidu Inc.（百度公司）；National Laboratory of Pattern Recognition (NLPR)（模式识别国家重点实验室）；Chinese Academy of Sciences Artificial Intelligence Research (CAS-AIR)（中国科学院人工智能研究院）
Video text detection is considered as one of the most difficult tasks in document analysis due to the following two challenges: 1) the difficulties caused by video scenes, i.e., motion blur, illumination changes, and occlusion; 2) the properties of text including variants of fonts, languages, orientations, and shapes. Most existing methods attempt to enhance the performance of video text detection by cooperating with video text tracking, but treat these two tasks separately. In this work, we propose an end-to-end video text detection model with online tracking to address these two challenges. …
Technical University of Munich（慕尼黑工业大学）；City University of Hong Kong（香港城市大学）；Inceptio X-Lab（嬴彻X实验室）
Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking. However, it is non-trivial to perform accurate target-specific detection since the point cloud of objects in raw LiDAR scans is usually sparse and incomplete. In this paper, we address this issue by explicitly leveraging temporal motion cues and propose DMT, a Detector-free Motion-prediction-based 3D Tracking network that completely removes the usage of complicated 3D detectors and is lighter, faster, and more accurate than p…
University of Surrey（萨里大学）；iFlyTek-Surrey Joint Research Centre on Artificial Intelligence（讯飞-萨里人工智能联合研究中心）；Surrey Institute for People-Centred Artificial Intelligence, University of Surrey（萨里大学以人为本人工智能研究所）
Existing temporal action detection (TAD) methods rely on large training data including segment-level annotations, limited to recognizing previously seen classes alone during inference. Collecting and annotating a large training set for each class of interest is costly and hence unscalable. Zero-shot TAD (ZS-TAD) resolves this obstacle by enabling a pre-trained model to recognize any unseen action classes. Meanwhile, ZS-TAD is also much more challenging with significantly less investigation. Inspired by the success of zero-shot image classification aided by vision-language (ViL) models such as …
Hanyang University（汉阳大学）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
In this paper, we propose a new joint object detection and tracking (JoDT) framework for 3D object detection and tracking based on camera and LiDAR sensors. The proposed method, referred to as 3D DetecTrack, enables the detector and tracker to cooperate to generate a spatio-temporal representation of the camera and LiDAR data, with which 3D object detection and tracking are then performed. The detector constructs the spatio-temporal features via the weighted temporal aggregation of the spatial features obtained by the camera and LiDAR fusion. Then, the detector reconfigures the initial detecti…
We introduce a tracking-by-detection method that integrates a deep object detector with a particle filter tracker under the regularization framework where the tracked object is represented by a sparse dictionary. A novel observation model which establishes consensus between the detector and tracker is formulated that enables us to update the dictionary with the guidance of the deep detector. This yields an efficient representation of the object appearance through the video sequence hence improves robustness to occlusion and pose changes. Moreover we propose a new state vector consisting of tra…
