Transformer-based single-object trackers achieve state-of-the-art accuracy but rely on fixed-depth inference, executing the full encoder--decoder stack for every frame regardless of visual complexity, thereby incurring unnecessary computational cost in long video sequences dominated by temporally coherent frames. We propose UncL-STARK, an architecture-preserving approach that enables dynamic, uncertainty-aware depth adaptation in transformer-based trackers without modifying the underlying network or adding auxiliary heads. The model is fine-tuned to retain predictive robustness at multiple intermediate depths using random-depth training with knowledge distillation, thus enabling safe inference-time truncation. At runtime, we derive a lightweight uncertainty estimate directly from the model's corner localization heatmaps and use it in a feedback-driven policy that selects the encoder and decoder depth for the next frame based on the prediction confidence by exploiting temporal coherence in video. Extensive experiments on GOT-10k and LaSOT demonstrate up to 12% GFLOPs reduction, 8.9% latency reduction, and 10.8% energy savings while maintaining tracking accuracy within 0.2% of the full-depth baseline across both short-term and long-term sequences.
Object tracking quality usually depends on video context (e.g. object occlusion level, object density). In order to decrease this dependency, this paper presents a learning approach to adapt the tracker parameters to the context variations. In an offline phase, satisfactory tracking parameters are learned for video context clusters. In the online control phase, once a context change is detected, the tracking parameters are tuned using the learned values. The experimental results show that the proposed approach outperforms the recent trackers in state of the art. This paper brings two contribut…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of gradient-descent during tracking while pruning its network channels using the target ground-truth at the first frame. Such a learning problem is formulated as a meta-learning task, where a meta-tracker is trained by updating its meta-parameters for initial weights, learning rates, and pruning masks through carefully designed tracking simulations. The integrated me…
Holistic object representation-based trackers suffer from performance drop under large appearance change such as deformation and occlusion. In this work, we propose a dynamic part-based tracker and constantly update the target part representation to adapt to object appearance change. Moreover, we design an attention-guided part localization network to directly predict the target part locations, and determine the final bounding box with the distribution of target parts. Our proposed tracker achieves promising results on various benchmarks: VOT2018, OTB100 and GOT-10k
Anhui University（安徽大学）；University of Chinese Academy of Sciences（中国科学院大学）
The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples independently while ignores the relationship information among them. In this paper, we propose a novel structure-aware deep neural network to overcome such limitations. In particular, we construct a graph to represent the pairwise relationships among training samples, and additionally take the natural language as the supervised information to learn both feature re…
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；School of Information Science and Technology, Lingnan Normal University（岭南师范学院信息科学与技术学院）；Beijing Laboratory of Intelligent Information Technology（北京智能信息技术实验室）
Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking. Following the tracking-by-detection framework, an online MILBoost approach is developed that sequentially chooses weak classifiers by maximizing the bag likelihood. In this paper, we extend this idea towards incorporating the instance significance estimation into the online MILBoost framework. First, instead of treating all instances equally, with each instance we associate a significance-coefficient that represents its contribution to the bag likelihood. The coefficients a…
Chongqing University（重庆大学）；State Key Laboratory of Mechanical Transmissions（机械传动国家重点实验室）
In the existing literature, most 3D multi-object tracking algorithms based on the tracking-by-detection framework employed deterministic tracks and detections for similarity calculation in the data association stage. Namely, the inherent uncertainties existing in tracks and detections are overlooked. In this work, we discard the commonly used deterministic tracks and deterministic detections for data association, instead, we propose to model tracks and detections as random vectors in which uncertainties are taken into account. Then, based on the Jensen-Shannon divergence, the similarity betwee…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Microsoft Research Asia（微软亚洲研究院）；The University of Hong Kong（香港大学）
Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot online adaptation methods incorporate the prior knowledge from large amounts of annotated training data via complex meta-learning optimization in the offline phase. This helps the online deep trackers to achieve fast adaptation and reduce overfitting risk in tracking. In this paper, we propose a simple yet effective recursive least-squares estimator-aided onli…
Online learning policy makes visual trackers more robust against different distortions through learning domain-specific cues. However, the trackers adopting this policy fail to fully leverage the discriminative context of the background areas. Moreover, owing to the lack of sufficient data at each time step, the online learning approach can also make the trackers prone to over-fitting to the background regions. In this paper, we propose a domain adaptation approach to strengthen the contributions of the semantic background context. The domain adaptation approach is backboned with only an off-t…
Object Tracking is one important problem in computer vision and surveillance system. The existing models mainly exploit the single-view feature (i.e. color, texture, shape) to solve the problem, failing to describe the objects comprehensively. In this paper, we solve the problem from multi-view perspective by leveraging multi-view complementary and latent information, so as to be robust to the partial occlusion and background clutter especially when the objects are similar to the target, meanwhile addressing tracking drift. However, one big problem is that multi-view fusion strategy can inevit…
In surveillance and search and rescue applications, it is important to perform multi-target tracking (MOT) in real-time on low-end devices. Today's MOT solutions employ deep neural networks, which tend to have high computation complexity. Recognizing the effects of frame sizes on tracking performance, we propose DeepScale, a model agnostic frame size selection approach that operates on top of existing fully convolutional network-based trackers to accelerate tracking throughput. In the training stage, we incorporate detectability scores into a one-shot tracker architecture so that DeepScale can…
School of Information and Communication Engineering, Xi’an Jiaotong University（西安交通大学信息与通信工程学院）
Object tracking has been studied for decades, but most of the existing works are focused on the short-term tracking. For a long sequence, the object is often fully occluded or out of view for a long time, and existing short-term object tracking algorithms often lose the target, and it is difficult to re-catch the target even if it reappears again. In this paper a novel long-term object tracking algorithm flow_MDNet_RPN is proposed, in which a tracking result judgement module and a detection module are added to the short-term object tracking algorithm. Experiments show that the proposed long-te…
Dalian University of Technology（大连理工大学）；The University of Sydney（悉尼大学）；China Science IntelliCloud Technology Co., Ltd（中科智云科技有限公司）
The fully-convolutional siamese network based on template matching has shown great potentials in visual tracking. During testing, the template is fixed with the initial target feature and the performance totally relies on the general matching ability of the siamese network. However, this manner cannot capture the temporal variations of targets or background clutter. In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations. Our algorithm performs fee…
Anhui University（安徽大学）；The University of Sydney（悉尼大学）；Peng Cheng Laboratory（鹏城实验室）；Peking University（北京大学）；University of Science and Technology of China（中国科学技术大学）
Most of the existing single object trackers track the target in a unitary local search window, making them particularly vulnerable to challenging factors such as heavy occlusions and out-of-view movements. Despite the attempts to further incorporate global search, prevailing mechanisms that cooperate local and global search are relatively static, thus are still sub-optimal for improving tracking performance. By further studying the local and global search results, we raise a question: can we allow more dynamics for cooperating both results? In this paper, we propose to introduce more dynamics …
Tongji University（同济大学）；the University of Hong Kong（香港大学）
Vision-based object tracking has boosted extensive autonomous applications for unmanned aerial vehicles (UAVs). However, the dynamic changes in flight maneuver and viewpoint encountered in UAV tracking pose significant difficulties, e.g. , aspect ratio change, and scale variation. The conventional cross-correlation operation, while commonly used, has limitations in effectively capturing perceptual similarity and incorporates extraneous background information. To mitigate these limitations, this work presents a novel saliency-guided dynamic vision Transformer (SGDViT) for UAV tracking. The prop…
University of Alberta（阿尔伯塔大学）；Yazd University（亚兹德大学）；Sharif University of Technology（谢里夫理工大学）
We consider the problem of tracking an unknown small target from aerial videos of medium to high altitudes. This is a challenging problem, which is even more pronounced in unavoidable scenarios of drastic camera motion and high density. To address this problem, we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-stream network and an offline reference proposal generation strategy. The proposed network fully exploits target-related information by multi-scale feature learning and attention modules. The proposed strategy introduces an efficient sampling strategy …
A saliency guided hierarchical visual tracking (SHT) algorithm containing global and local search phases is proposed in this paper. In global search, a top-down saliency model is novelly developed to handle abrupt motion and appearance variation problems. Nineteen feature maps are extracted first and combined with online learnt weights to produce the final saliency map and estimated target locations. After the evaluation of integration mechanism, the optimum candidate patch is passed to the local search. In local search, a superpixel based HSV histogram matching is performed jointly with an L2…
National University of Singapore（新加坡国立大学）；Interactive Digital Media Institute（互动数字媒体研究所）
In this paper, a robust visual tracking approach via mixed model based convolutional neural networks (SDT) is developed. In order to handle abrupt or fast motion, a prior map is generated to facilitate the localization of region of interest (ROI) before the deep tracker is performed. A top-down saliency model with nineteen shallow cues are employed to construct the prior map with online learnt combination weights. Moreover, apart from a holistic deep learner, four local networks are also trained to learn different components of the target. The generated four local heat maps will facilitate to …
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead develops a novel unsupervised domain adaptation framework for nighttime aerial tracking (named UDAT). Specifically, a unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. To tackle the domain discrepancy, we employ a Transformer-based bridging layer post to the feature extractor to align image features fro…
Parameter tuning is a common issue for many tracking algorithms. In order to solve this problem, this paper proposes an online parameter tuning to adapt a tracking algorithm to various scene contexts. In an offline training phase, this approach learns how to tune the tracker parameters to cope with different contexts. In the online control phase, once the tracking quality is evaluated as not good enough, the proposed approach computes the current context and tunes the tracking parameters using the learned values. The experimental results show that the proposed approach improves the performance…
Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preserving consideration or bandwidth limitation. Source-free domain adaptation aims to solve the above problem by performing domain adaptation without accessing the source data. The adaptation paradigm is receiving more and more attention in recent years, and multiple works have been proposed for unsupervised source-free domain adaptation. However, without utilizing any supervised s…
Jiangxi Normal University（江西师范大学）；Toyota Research Institute of North America（丰田北美研究院）；University of Electronic Science and Technology of China（电子科技大学）；Australian National University（澳大利亚国立大学）
Visual tracking is a fundamental problem in computer vision. Recently, some deep-learning-based tracking algorithms have been achieving record-breaking performances. However, due to the high complexity of deep learning, most deep trackers suffer from low tracking speed, and thus are impractical in many real-world applications. Some new deep trackers with smaller network structure achieve high efficiency while at the cost of significant decrease on precision. In this paper, we propose to transfer the feature for image classification to the visual tracking domain via convolutional channel reduct…
Multimedia Laboratory, The Chinese University of Hong Kong（香港中文大学多媒体实验室）；The University of Hong Kong（香港大学）
In this technical report, we present the top-performing LiDAR-only solutions for 3D detection, 3D tracking and domain adaptation three tracks in Waymo Open Dataset Challenges 2020. Our solutions for the competition are built upon our recent proposed PV-RCNN 3D object detection framework. Several variants of our PV-RCNN are explored, including temporal information incorporation, dynamic voxelization, adaptive training sample selection, classification with RoI features, etc. A simple model ensemble strategy with non-maximum-suppression and box voting is adopted to generate the final results. By …
Automatically detecting, labeling, and tracking objects in videos depends first and foremost on accurate category-level object detectors. These might, however, not always be available in practice, as acquiring high-quality large scale labeled training datasets is either too costly or impractical for all possible real-world application scenarios. A scalable solution consists in re-using object detectors pre-trained on generic datasets. This work is the first to investigate the problem of on-line domain adaptation of object detectors for causal multi-object tracking (MOT). We propose to alleviat…
Kyushu University（九州大学）；Kyoto University（京都大学）；The University of Tokyo（东京大学）
Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a small number of labeled samples from the target domain. In this paper, we develop a semi-supervised domain adaptation method, which has robustness to class-imbalanced situations, which are common in medical image classification tasks. For robustness, we propose a weakly-supervised clustering pipeline to obtain high-purity clusters and utilize the clusters in representation learning for domain adaptation. The proposed …
Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation
Pengcheng Laboratory（鹏城实验室）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；South China University of Technology（华南理工大学）；Pazhou Lab (Huangpu)（琶洲实验室（黄埔））；UC Merced（加州大学默塞德分校）；Yonsei University（延世大学）
Peking University（北京大学）；South China University of Technology（华南理工大学）；National University of Singapore（新加坡国立大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
This paper studies a new, practical but challenging problem, called Class-Incremental Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all classes, but the classes in the unlabeled target domain increase sequentially. This problem is challenging due to two difficulties. First, source and target label sets are inconsistent at each time step, which makes it difficult to conduct accurate domain alignment. Second, previous target classes are unavailable in the current step, resulting in the forgetting of previous knowledge. To address this problem, we propose a nov…
NELVT, School of EE & CS, Peking University（北京大学电子信息与计算机科学学院NELVT）；University of Chinese Academy of Sciences（中国科学院大学）；School of ECE, Peking University（北京大学电子信息工程学院）；Pengcheng Laboratory（鹏城实验室）；Beijing Institute of Technology（北京理工大学）；Nanyang Technological University（南洋理工大学）
Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. However, existing UDA methods largely ignore the instantaneous data distribution during model learning, which could deteriorate the feature representation given large domain shift. In this work, we propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains while considering the instantaneous alignment difficulty. The core of SGA is to calculate "hardness" factors for samp…
Beijing Laboratory of Advanced Information Networks（北京先进信息网络实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）；Horizon Robotics（地平线机器人）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Human pose estimation has witnessed a significant advance thanks to the development of deep learning. Recent human pose estimation approaches tend to directly predict the location heatmaps, which causes quantization errors and inevitably deteriorates the performance within the reduced network output. Aim at solving it, we revisit the heatmap-offset aggregation method and propose the Offset-guided Network (OGN) with an intuitive but effective fusion strategy for both two-stages pose estimation and Mask R-CNN. For two-stages pose estimation, a greedy box generation strategy is also proposed to k…
Layer-Guided UAV Tracking: Enhancing Efficiency and Occlusion Robustness
Department of Control Science and Engineering, University of Shanghai for Science and Technology（上海理工大学控制科学与工程学院）；Busness School, University of Shanghai for Science and Technology（上海理工大学商学院）
State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences（中国科学院软件研究所计算机科学国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Machine Intelligence Technology Lab Alibaba Group（阿里巴巴集团机器智能技术实验室）
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions. This paper describes our solution to the Track 3 multi-camera vehicle tracking task in 2021 AI City Challenge (AICITY21). This paper proposes a multi-target multi-camera vehicle tracking framework guided by the crossroad zones. The framework includes: (1) Use mature detection and vehicle re-identification models to extract targets and appearance features. (2) Use modified JDETracker (without detection module) to track single-camera vehicles and generate single-came…
Deep neural networks have significantly improved appearance-based gaze estimation accuracy. However, it still suffers from unsatisfactory performance when generalizing the trained model to new domains, e.g., unseen environments or persons. In this paper, we propose a plug-and-play gaze adaptation framework (PnP-GA), which is an ensemble of networks that learn collaboratively with the guidance of outliers. Since our proposed framework does not require ground-truth labels in the target domain, the existing gaze estimation networks can be directly plugged into PnP-GA and generalize the algorithms…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland University（萨尔大学）；Aalto University（阿尔托大学）
Markerless tracking of hands and fingers is a promising enabler for human-computer interaction. However, adoption has been limited because of tracking inaccuracies, incomplete coverage of motions, low framerate, complex camera setups, and high computational requirements. In this paper, we present a fast method for accurately tracking rapid and complex articulations of the hand using a single depth camera. Our algorithm uses a novel detection-guided optimization strategy that increases the robustness and speed of pose estimation. In the detection step, a randomized decision forest classifies pi…
Nip Rumors in the Bud: Retrieval-Guided Topic-Level Adaptation for Test-Time Fake News Video Detection
University of Electronic Science and Technology of China（电子科技大学）；Aiwen Technology Co., Ltd.（爱文科技有限公司）；Intelligent Digital Media Technology Key Laboratory of Sichuan Province（四川省智能数字媒体技术重点实验室）
Domain adaptation (DA) or domain generalization (DG) for face presentation attack detection (PAD) has attracted attention recently with its robustness against unseen attack scenarios. Existing DA/DG-based PAD methods, however, have not yet fully explored the domain-specific style information that can provide knowledge regarding attack styles (e.g., materials, background, illumination and resolution). In this paper, we introduce a novel Style-Guided Domain Adaptation (SGDA) framework for inference-time adaptive PAD. Specifically, Style-Selective Normalization (SSN) is proposed to explore the do…
