Generic Event Boundary Detection (GEBD) aims to identify moments in videos that humans perceive as event boundaries. This paper proposes a novel method for addressing this task, called Structured Context Learning, which introduces the Structured Partition of Sequence (SPoS) to provide a structured context for learning temporal information. Our approach is end-to-end trainable and flexible, not restricted to specific temporal models like GRU, LSTM, and Transformers. This flexibility enables our method to achieve a better speed-accuracy trade-off. Specifically, we apply SPoS to partition the input frame sequence and provide a structured context for the subsequent temporal model. Notably, SPoS’s overall computational complexity is linear with respect to the video length. We next calculate group similarities to capture differences between frames, and a lightweight fully convolutional network is utilized to determine the event boundaries based on the grouped similarity maps. To remedy the ambiguities of boundary annotations, we adapt the Gaussian kernel to preprocess the ground-truth event boundaries. Our proposed method has been extensively evaluated on the challenging Kinetics-GEBD, TAPOS, and shot transition detection datasets, demonstrating its superiority over existing state-of-the-art methods.

Camera-only multi-view 3D object detection in autonomous driving has witnessed encouraging developments in recent years, largely attributed to the revolution of fundamental architectures in modeling bird’s eye view (BEV). Despite the growing overall average performance, we contend that the exploration of more specific and challenging corner cases hasn’t received adequate attention. In this work, we delve into a specific yet critical issue for safe autonomous driving: occlusion. To alleviate this challenge, we draw inspiration from the human amodal perception system, which is proven to have the capacity for mentally reconstructing the complete semantic concept of occluded objects with prior knowledge. More specifically, we introduce auxiliary visual and language prototypes, akin to human prior knowledge, to enhance the diminished object features caused by occlusion. Inspired by Siamese object tracking, we fuse the information from these prototypes with the baseline model through an efficient depth-wise correlation, thereby enhancing the quality of object-related features and guiding the learning of 3D object queries, especially for partially occluded ones. Furthermore, we propose the random pixel drop to mimic occlusion and the multi-modal contrastive loss to align visual features of different occlusion levels to a unified space during training. Our inspiration originates from addressing occlusion, however, we are surprised to find that the proposed framework also enhances robustness in various challenging scenarios that diminish object representation, such as inclement weather conditions. By applying our model to different baselines, i.e., BEVFormer and SparseBEV, we demonstrate consistent improvements.

Egocentric visual query localization (EgoVQL) focuses on localizing the target of interest in space and time from first-person videos, given a visual query. Despite recent progressive, existing methods often struggle to handle severe object appearance changes and cluttering background in the video due to lacking sufficient target cues, leading to degradation. Addressing this, we introduce PRVQL, a novel Progressive knowledge-guided Refinement framework for EgoVQL. The core is to continuously exploit target-relevant knowledge directly from videos and utilize it as guidance to refine both query and video features for improving target localization. Our PRVQL contains multiple processing stages. The target knowledge from one stage, comprising appearance and spatial knowledge extracted via two specially designed knowledge learning modules, are utilized as guidance to refine the query and videos features for the next stage, which are used to generate more accurate knowledge for further feature refinement. With such a progressive process, target knowledge in PRVQL can be gradually improved, which, in turn, leads to better refined query and video features for localization in the final stage. Compared to previous methods, our PRVQL, besides the given object cues, enjoys additional crucial target information from a video as guidance to refine features, and hence enhances EgoVQL in complicated scenes. In our experiments on challenging Ego4D, PRVQL achieves state-of-the-art result and largely surpasses other methods, showing its efficacy. Our code, model and results will be released at https://github.com/fb-reps/PRVQL.

In this paper, we present a novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild. Specifically, GSOT3D offers 620 sequences with 123K frames, and covers a wide selection of 54 object categories. Each sequence is offered with multiple modalities, including the point cloud (PC), RGB image, and depth. This allows GSOT3D to support various 3D tracking tasks, such as single-modal 3D SOT on PC and multi-modal 3D SOT on RGB-PC or RGB-D, and thus greatly broadens research directions for 3D object tracking. To provide highquality per-frame 3D annotations, all sequences are labeled manually with multiple rounds of meticulous inspection and refinement. To our best knowledge, GSOT3D is the largest benchmark dedicated to various generic 3D object tracking tasks. To understand how existing 3D trackers perform and to provide comparisons for future research on GSOT3D, we assess eight representative point cloud-based tracking models. Our evaluation results exhibit that these models heavily degrade on GSOT3D, and more efforts are required for robust and generic 3D object tracking. Besides, to encourage future research, we present a simple yet effective generic 3D tracker, named PROT3D, that localizes the target object via a progressive spatial-temporal network and outperforms all current solutions by a large margin. By releasing GSOT3D, we expect to advance further 3D tracking in future research and applications. Our benchmark and model as well as the evaluation results will be publicly released at our webpage https://github.com/ailovejinx/GSOT3D.

Open-Vocabulary Multi-Object Tracking (OV-MOT) aims to enable approaches to track objects without being limited to a predefined set of categories. Current OV-MOT methods typically rely primarily on instance-level detection and association, often overlooking trajectory information that is unique and essential for object tracking tasks. Utilizing trajectory information can enhance association stability and classification accuracy, especially in cases of occlusion and category ambiguity, thereby improving adaptability to novel classes. Thus motivated, in this paper we propose \textbf{TRACT}, an open-vocabulary tracker that leverages trajectory information to improve both object association and classification in OV-MOT. Specifically, we introduce a \textit{Trajectory Consistency Reinforcement} (\textbf{TCR}) strategy, that benefits tracking performance by improving target identity and category consistency. In addition, we present \textbf{TraCLIP}, a plug-and-play trajectory classification module. It integrates \textit{Trajectory Feature Aggregation} (\textbf{TFA}) and \textit{Trajectory Semantic Enrichment} (\textbf{TSE}) strategies to fully leverage trajectory information from visual and language perspectives for enhancing the classification results. Extensive experiments on OV-TAO show that our TRACT significantly improves tracking performance, highlighting trajectory information as a valuable asset for OV-MOT. Code will be released.

Transformer has attracted increasing interest in spatio-temporal video grounding, or STVG, owing to its end-to-end pipeline and promising result. Existing Transformer-based STVG approaches often leverage a set of object queries, which are initialized simply using zeros and then gradually learn target position information via iterative interactions with multimodal features, for spatial and temporal localization. Despite simplicity, these zero object queries, due to lacking target-specific cues, are hard to learn discriminative target information from interactions with multimodal features in complicated scenarios (e.g., with distractors or occlusion), resulting in degradation. Addressing this, we introduce a novel $\textbf{T}$arget-$\textbf{A}$ware Transformer for $\textbf{STVG}$ ($\textbf{TA-STVG}$), which seeks to adaptively generate object queries via exploring target-specific cues from the given video-text pair, for improving STVG. The key lies in two simple yet effective modules, comprising text-guided temporal sampling (TTS) and attribute-aware spatial activation (ASA), working in a cascade. The former focuses on selecting target-relevant temporal cues from a video utilizing holistic text information, while the latter aims at further exploiting the fine-grained visual attribute information of the object from previous target-aware temporal cues, which is applied for object query initialization. Compared to existing methods leveraging zero-initialized queries, object queries in our TA-STVG, directly generated from a given video-text pair, naturally carry target-specific cues, making them adaptive and better interact with multimodal features for learning more discriminative information to improve STVG. In our experiments on three benchmarks, including HCSTVG-v1/-v2 and VidSTG, TA-STVG achieves state-of-the-art performance and significantly outperforms the baseline, validating its efficacy. Moreover, TTS and ASA are designed for general purpose. When applied to existing methods such as TubeDETR and STCAT, we show substantial performance gains, verifying its generality. Code is released at https://github.com/HengLan/TA-STVG.

Recent advancements in visual object tracking have markedly improved the capabilities of unmanned aerial vehicle (UAV) tracking, which is a critical component in real-world robotics applications. While the integration of hierarchical lightweight networks has become a prevalent strategy for enhancing efficiency in UAV tracking, it often results in a significant drop in network capacity, which further exacerbates challenges in UAV scenarios, such as frequent occlusions and extreme changes in viewing angles. To address these issues, we introduce a novel family of UAV trackers, termed CGTrack, which combines explicit and implicit techniques to expand network capacity within a coarse-to-fine framework. Specifically, we first introduce a Hierarchical Feature Cascade (HFC) module that leverages the spirit of feature reuse to increase network capacity by integrating the deep semantic cues with the rich spatial information, incurring minimal computational costs while enhancing feature representation. Based on this, we design a novel Lightweight Gated Center Head (LGCH) that utilizes gating mechanisms to decouple target-oriented coordinates from previously expanded features, which contain dense local discriminative information. Extensive experiments on three challenging UAV tracking benchmarks demonstrate that CGTrack achieves state-of-the-art performance while running fast. Code will be available at https://github.com/Nightwatch-Fox11/CGTrack.

Vision-Language MOT is a critical tracking problem that has recently garnered increasing attention. It aims to track objects based on human language commands, displacing the traditional use of templates or pre-set information from training sets in conventional tracking tasks. However, a key challenge remains in understanding why language is used for tracking, hindering further development. In this paper, we introduce Language-Guided MOT, a unified task framework, and LaMOT, a corresponding large-scale benchmark, which encompasses diverse scenarios and language descriptions and comprises 1,660 sequences from 4 different datasets. The purpose of LaMOT is to unify various Vision-Language MOT tasks while providing a standardized evaluation platform. To ensure high-quality annotations, we manually assign appropriate descriptive texts to each target in every video and conduct careful inspection and correction. To our knowledge, LaMOt is the first benchmark dedicated to Language-Guided MOT. Additionally, we propose a simple yet effective tracker, termed LaMOTer. By establishing a unified task framework, providing challenging benchmarks, and offering insights for future algorithm design and evaluation, we expect to contribute to the advancement of research in Vision-Language MOT. We will release the data at https://github.com/Nathan-Li123/LaMOT.

This paper tackles the challenging problem of semi-supervised monocular 3D object detection with a general framework. In specific, having observed that the bottleneck of this task lies in lacking reliable and informative samples from unlabeled data for detector learning, we introduce a novel simple yet effective ‘Augment and Criticize’ pipeline that mines abundant informative samples for robust detection. To be more specific, in the ‘Augment’ stage, we present the Augmentation-based Prediction aGgregation (APG), which applies automatically learned transformations to unlabeled images and aggregates detections from various augmented views as pseudo labels. Since not all the pseudo labels from APG are beneficially informative, the subsequent ‘Criticize’ phase is introduced. Particularly, we present the Critical Retraining Strategy (CRS) that, unlike simply filtering pseudo labels using a fixed threshold, employs a learnable network to evaluate the contribution of unlabeled images at different training timestamps. This way, the noisy samples prohibitive to model evolution can be effectively suppressed. In order to validate ‘Augment-Criticize’, we apply it to MonoDLE [1] and MonoFlex [2], and the two new detectors, dubbed 3DSeMoDLEand 3DSeMoFLEX, achieve state-of-the-art results with consistent improvements, evidencing its effectiveness and generality.

High-performance Transformer trackers have exhibited excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and conveniently reduce computations without changing the model, an easy solution is to adopt a low-resolution input for efficient Transformer tracking. Albeit faster, this hurts tracking accuracy much due to the information loss in low resolution tracking. In this paper, we aim to mitigate such information loss to boost performance of low-resolution Transformer tracking via dual knowledge distillation from a frozen high-resolution (but not a larger) Transformer tracker. The core lies in two simple yet effective distillation modules, including query-key-value knowledge distillation (QKV-KD) and discrimination knowledge distillation (Disc-KD), across resolutions. The former, from the global view, allows the low-resolution tracker to inherit features and interactions from the high-resolution tracker, while the later, from the target-aware view, enhances the target-background distinguishing capacity via imitating discriminative regions from its high-resolution counterpart. With dual knowledge distillation, our Low-Resolution Transformer Tracker, dubbed LoReTrack, enjoys not only high efficiency owing to reduced computation but also enhanced accuracy by distilling knowledge from the high-resolution tracker. In extensive experiments, LoReTrack with a 2562resolution consistently improves baseline with the same resolution, and shows competitive or better results compared to the 3842high-resolution Transformer tracker, while running 52% faster and saving 56% MACs. Moreover, LoReTrack is resolution-scalable. With a 1282resolution, it runs 25 fps on a CPU with SUC scores of 64.9%/46.4% on LaSOT/LaSOText, surpassing other CPU real-time trackers. Code is released at https://github.com/ShaohuaDong2021/LoReTrack.

Graph Convolutional Networks (GCNs) have proven to be highly effective for skeleton-based action recognition, primarily due to their ability to leverage graph topology for feature aggregation, a key factor in extracting meaningful representations. However, despite their success, GCNs often struggle to effectively distinguish between ambiguous actions, revealing limitations in the representation of learned topological and spatial features. To address this challenge, we propose a novel approach, Gaussian Topology Refinement Gated Graph Convolution (G3CN), to address the challenge of distinguishing ambiguous actions in skeleton-based action recognition. G3CN incorporates a Gaussian filter to refine the skeleton topology graph, improving the representation of ambiguous actions. Additionally, Gated Recurrent Units (GRUs) are integrated into the GCN framework to enhance information propagation between skeleton points. Our method shows strong generalization across various GCN backbones. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA benchmarks demonstrate that G3CN effectively improves action recognition, particularly for ambiguous samples.

Establishing object-level correspondence between egocentric and exocentric views is essential for intelligent assistants to deliver precise and intuitive visual guidance. However, this task faces numerous challenges, including extreme viewpoint variations, occlusions, and the presence of small objects. Existing approaches usually borrow solutions from video object segmentation models, but still suffer from the aforementioned challenges. Recently, the Segment Anything Model 2 (SAM 2) has shown strong generalization capabilities and excellent performance in video object segmentation. Yet, when simply applied to the ego-exo correspondence (EEC) task, SAM 2 encounters severe difficulties due to ineffective ego-exo feature fusion and limited long-term memory capacity, especially for long videos. Addressing these problems, we propose a novel EEC framework based on SAM 2 with long-term memories by presenting a dual-memory architecture and an adaptive feature routing module inspired by Mixture-of-Experts (MoE). Compared to SAM 2, our approach features **(i)** a Memory-View MoE module which consists of a dual-branch routing mechanism to adaptively assign contribution weights to each expert feature along both channel and spatial dimensions, and **(ii)** a dual-memory bank system with a simple yet effective compression strategy to retain critical long-term information while eliminating redundancy. In the extensive experiments on the challenging EgoExo4D benchmark, our method, dubbed ***LM-EEC***, achieves new state-of-the-art results and significantly outperforms existing methods and the SAM 2 baseline, showcasing its strong generalization across diverse scenarios. Our code and model are available at https://github.com/juneyeeHu/LM-EEC.

Transformer-based algorithms, such as LoRAT, have significantly enhanced object-tracking performance. However, these approaches rely on a standard attention mechanism, which incurs quadratic token complexity, making real-time inference computationally expensive. In this paper, we introduce LoRATv2, a novel tracking framework that addresses these limitations with three main contributions. First, LoRATv2 integrates frame-wise causal attention, which ensures full self-attention within each frame while enabling causal dependencies across frames, significantly reducing computational overhead. Moreover, key-value (KV) caching is employed to efficiently reuse past embeddings for further speedup. Second, building on LoRAT's parameter-efficient fine-tuning, we propose Stream-Specific LoRA Adapters (SSLA). As frame-wise causal attention introduces asymmetry in how streams access temporal information, SSLA assigns dedicated LoRA modules to the template and each search stream, with the main ViT backbone remaining frozen. This allows specialized adaptation for each stream's role in temporal tracking. Third, we introduce a two-phase progressive training strategy, which first trains a single-search-frame tracker and then gradually extends it to multi-search-frame inputs by introducing additional LoRA modules. This curriculum-based learning paradigm improves long-term tracking while maintaining training efficiency. In extensive experiments on multiple benchmarks, LoRATv2 achieves state-of-the-art performance, substantially improved efficiency, and a superior performance-to-FLOPs ratio over state-of-the-art trackers. The code is available at https://github.com/LitingLin/LoRATv2.

Prompt-based learning has emerged as a parameter-efficient finetuning (PEFT) approach to facilitate Large Language Model (LLM) adaptation to downstream tasks by conditioning generation with task-aware guidance. Despite its successes, current prompt-based learning methods heavily rely on laborious grid searching for optimal prompt length and typically require considerable number of prompts, introducing additional computational burden. Worse yet, our pioneer findings indicate that the task-aware prompt design is inherently limited by its absence of instance-aware information, leading to a subtle attention interplay with the input sequence. In contrast, simply incorporating instance-aware information as a part of the guidance can enhance the prompt-tuned model performance without additional fine-tuning. Moreover, we find an interesting phenomenon, namely "attention anchor", that incorporating instance-aware tokens at the earliest position of the sequence can successfully preserve strong attention to critical structural information and exhibit more active attention interaction with all input tokens. In light of our observation, we introduce Capsule Prompt-Tuning (CaPT), an efficient and effective solution that leverages off-the-shelf, informative instance semantics into prompt-based learning. Our approach innovatively integrates both instance-aware and task-aware information in a nearly parameter-free manner (i.e., one single capsule prompt). Empirical results demonstrate that our method can exhibit superior performance across various language tasks (e.g., 84.03\% average accuracy on T5-Large), serving as an "attention anchor," while enjoying high parameter efficiency (e.g., 0.003\% of model parameters on Llama3.2-1B).

Multiobject tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender, hairstyle, body shape, and clothing features, which contain rich and high-level information, have been less explored. To address this gap, we propose a simple, effective, and generic method to predict pedestrian attributes to support general reidentification (Re-ID) embedding. We first introduce attribute multi-object tracking (AttMOT), a large, highly enriched synthetic dataset for pedestrian tracking, containing over 80k frames and six million pedestrian identity switches (IDs) with different times, weather conditions, and scenarios. To the best of authors' knowledge, AttMOT is the first MOT dataset with semantic attributes. Subsequently, we explore different approaches to fuse Re-ID embedding and pedestrian attributes, including attention mechanisms, which we hope will stimulate the development of attribute-assisted MOT. The proposed method attribute-assisted method (AAM) demonstrates its effectiveness and generality on several representative pedestrian MOT benchmarks, including MOT17 and MOT20, through experiments on the AttMOT dataset. When applied to the state-of-the-art trackers, AAM achieves consistent improvements in multi-object tracking accuracy (MOTA), higher order tracking accuracy (HOTA), association accuracy (AssA), IDs, and IDF1 scores. For instance, on MOT17, the proposed method yields a +1.1 MOTA, +1.7 HOTA, and +1.8 IDF1 improvement when used with FairMOT. To further encourage related research, we release the data and code at https://github.com/HengLan/AttMOT.

Spatio-temporal video grounding (or STVG) task aims at locating a spatio-temporal tube for a specific instance given a text query. Despite advancements, current methods easily suffer the distractors or heavy object appearance variations in videos due to insufficient object information from the text, leading to degradation. Addressing this, we propose a novel framework, context-guided STVG (CG-STVG), which mines discriminative instance context for object in videos and applies it as a supplementary guidance for target localization. The key of CG-STVG lies in two specially designed modules, including instance context generation (ICG), which focuses on discovering visual context information (in both appearance and motion) of the instance, and instance context refinement (ICR), which aims to improve the instance context from ICG by eliminating irrelevant or even harmful information from the context. During grounding, ICG, together with ICR, are deployed at each decoding stage of a transformer architecture for instance context learning. Particularly, instance context learned from one decoding stage is fed to the next stage, and leveraged as a guidance containing rich and discriminative object feature to enhance the target-awareness in decoding feature, which conversely benefits generating better new instance context to improve localization finally. Compared to existing methods, CG-STVG enjoys object information in text query and guidance from mined instance visual context for more accurate target localization. In experiments on HCSTVG-v1/-v2 and VidSTG, CG-STVG sets new state-of-the-arts in m_tIoU and m_vIoU on all of them, showing efficacy. Code is released at https://github.com/HengLan/CGSTVG.

In this work, we introduce PRoMoTION, a unified proto-typical transformer-based framework engineered to model fundamental motion tasks. PRoMoTION offers a range of compelling attributes that set it apart from current task-specific paradigms. (1) We adopt a prototypical perspective, establishing a unified paradigm that harmonizes disparate motion learning approaches. This novel paradigm stream-lines the architectural design, enabling the simultaneous assimilation of diverse motion information. (2) We capitalize on a dual mechanism involving the feature denoiser and the prototypical learner to decipher the intricacies of motion. This approach effectively circumvents the pitfalls of ambiguity in pixel-wise feature matching, significantly bolstering the robustness of motion representation. (3)) We demon-strate a profound degree of transferability across distinct motion patterns. This inherent versatility reverberates robustly across a comprehensive spectrum of both 2D and 3D downstream tasks. Empirical results demonstrate that PRoMOTION outperforms various well-known specialized architectures, achieving 0.54 and 0.054$AbsRel$error on the Sintel and KITTI depth datasets, 1.04 and 2.01 average endpoint error on the clean and final pass of Sintel flow benchmark, and 4.30 F1-all error on the KITTI flow bench-mark. For its efficacy, we hope our work can catalyze a paradigm shift in universal models in computer vision.

Segmentation-based scene text detection algorithms that are accurate to the pixel level can satisfy the detection of arbitrary shape scene text and have received widespread attention. On the one hand, due to the complexity and di-versity of the scene text, the convolution with a fixed kernel size has some limitations in extracting the visual features of the scene text. On the other hand, most of the existing segmentation-based algorithms only segment the center of the text, losing information such as the edges and directions of the text, with limited detection accuracy. There are also some improved algorithms that use iterative cor-rections or introduce other multiple information to improve text detection accuracy but at the expense of efficiency. To address these issues, this paper proposes a simple and effective scene text detection method, the Kernel Adaptive Con-volution, which is designed with a Kernel Adaptive Con-volution Module for scene text detection via predicting the distance map. Specifically, first, we design an extensible kernel adaptive convolution module (KACM) to extract vi-sual features from multiple convolutions with different ker-nel sizes in an adaptive manner. Secondly, our method pre-dicts the text distance map under the supervision of a pri-ori information (including direction map, and foreground segmentation map) and completes the text detection from the predicted distance map. Experiments on four publicly available datasets prove the effectiveness of our algorithm, in which the accuracy and efficiency of both the Total- Text and TD500 outperform the state-of-the-art algorithm. The algorithm efficiency is improved while the accuracy is com-petitive on ArT and CTW1500.

Vanilla image completion approaches exhibit sensitivity to large missing regions, attributed to the limited availability of reference information for plausible generation. To mitigate this, existing methods incorporate the extra cue as guidance for image completion. Despite improvements, these approaches are often restricted to employing a *single modality* (e.g., *segmentation* or *sketch* maps), which lacks scalability in leveraging multi-modality for more plausible completion. In this paper, we propose a novel, simple yet effective method for **M**ulti-mod**a**l **G**uided **I**mage **C**ompletion, dubbed **MaGIC**, which not only supports a wide range of single modality as the guidance (e.g., *text*, *canny edge*, *sketch*, *segmentation*, *depth*, and *pose*), but also adapts to arbitrarily customized combinations of these modalities (i.e., *arbitrary multi-modality*) for image completion. For building MaGIC, we first introduce a modality-specific conditional U-Net (MCU-Net) that injects single-modal signal into a U-Net denoiser for single-modal guided image completion. Then, we devise a consistent modality blending (CMB) method to leverage modality signals encoded in multiple learned MCU-Nets through gradient guidance in latent space. Our CMB is *training-free*, thereby avoiding the cumbersome joint re-training of different modalities, which is the secret of MaGIC to achieve exceptional flexibility in accommodating new modalities for completion. Experiments show the superiority of MaGIC over state-of-the-art methods and its generalization to various completion tasks.

Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approaches often fully fine-tune a dual-branch encoder-decoder framework with a complicated feature fusion strategy for achieving multimodal semantic segmentation, which is training-costly due to the massive parameter updates in feature extraction and fusion. To address this issue, we propose a surprisingly simple yet effective dual-prompt learning network (dubbed DPLNet) for training-efficient multimodal (e.g., RGBD/T) semantic segmentation. The core of DPLNet is to directly adapt a frozen pre-trained RGB model to multimodal semantic segmentation, reducing parameter updates. For this purpose, we present two prompt learning modules, comprising multimodal prompt generator (MPG) and multimodal feature adapter (MFA). MPG works to fuse the features from different modalities in a compact manner and is inserted from shallow to deep stages to generate the multi-level multimodal prompts that are injected into the frozen backbone, while MFA adapts prompted multimodal features in the frozen backbone for better multimodal semantic segmentation. Since both the MPG and MFA are lightweight, only a few trainable parameters (3.88M, 4.4% of the pre-trained backbone parameters) are introduced for multimodal feature fusion and learning. Using a simple decoder (3.27M parameters), DPLNet achieves new state-of-the-art performance or is on a par with other complex approaches on four RGB-D/T semantic segmentation datasets while satisfying parameter efficiency. Moreover, we show DPLNet is general and applicable to other multimodal segmentation tasks. Without special design, DPLNet outperforms many complicated models. The source code can be found at https://github.com/ShaohuaDong2021/DPLNet.

Cooperative perception for connected and automated vehicles is traditionally achieved through the fusion of feature maps from two or more vehicles. However, the absence of feature maps shared from other vehicles can lead to a significant decline in 3D object detection performance for cooperative perception models compared to standalone 3D detection models. This drawback impedes the adoption of cooperative perception as vehicle resources are often insufficient to concurrently employ two perception models. To tackle this issue, we present Simultaneous Individual and Cooperative Perception (SiCP), a generic framework that supports a wide range of the state-of-the-art standalone perception backbones and enhances them with a novel Dual-Perception Network (DP-Net) designed to facilitate both individual and cooperative perception. In addition to its lightweight nature with only 0.13M parameters, DP-Net is robust and retains crucial gradient information during feature map fusion. As demonstrated in a comprehensive evaluation on the V2V4Real and OPV2V datasets, thanks to DP-Net, SiCP surpasses state-of-the-art cooperative perception solutions while preserving the performance of standalone perception solutions. The source code can be found at https://github.com/DarrenQu/SiCP.

In this paper, we propose a novel benchmark, named VastTrack, aiming to facilitate the development of general visual tracking via encompassing abundant classes and videos. VastTrack consists of a few attractive properties: (1) Vast Object Category. In particular, it covers targets from 2,115 categories, significantly surpassing object classes of existing popular benchmarks (e.g., GOT-10k with 563 classes and LaSOT with 70 categories). Through providing such vast object classes, we expect to learn more general object tracking. (2) Larger scale. Compared with current benchmarks, VastTrack provides 50,610 videos with 4.2 million frames, which makes it to date the largest dataset in term of the number of videos, and hence could benefit training even more powerful visual trackers in the deep learning era. (3) Rich Annotation. Besides conventional bounding box annotations, VastTrack also provides linguistic descriptions with more than 50K sentences for the videos. Such rich annotations of VastTrack enable the development of both vision-only and vision-language tracking. In order to ensure precise annotation, each frame in the videos is manually labeled with multi-stage of careful inspections and refinements. To understand performance of existing trackers and to provide baselines for future comparison, we extensively evaluate 25 representative trackers. The results, not surprisingly, display significant drops compared to those on current datasets due to lack of abundant categories and videos from diverse scenarios for training, and more efforts are urgently required to improve general visual tracking. Our VastTrack, the toolkit, and evaluation results are publicly available at https://github.com/HengLan/VastTrack.

Abstract We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation. Codes and models will be released.

Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from recent flourishing VL learning. We argue that the reasons are two-fold: the lack of large-scale vision-language annotated videos and ineffective vision-language interaction learning of current works. These nuisances motivate us to design more effective vision-language representation for tracking, meanwhile constructing a large database with language annotation for model learning. Particularly, in this paper, we first propose a general attribute annotation strategy to decorate videos in six popular tracking benchmarks, which contributes a large-scale vision-language tracking database with more than 23,000 videos. We then introduce a novel framework to improve tracking by learning a unified-adaptive VL representation, where the cores are the proposed asymmetric architecture search and modality mixer (ModaMixer). To further improve VL representation, we introduce a contrastive loss to align different modalities. To thoroughly evidence the effectiveness of our method, we integrate the proposed framework on three tracking methods with different designs, i.e., the CNN-based SiamCAR (Guo et al. 2020), the Transformer-based OSTrack (Ye et al. 2022), and the hybrid structure TransT (Chen et al. 2021). The experiments demonstrate that our framework can significantly improve all baselines on six benchmarks. Besides empirical results, we theoretically analyze our approach to show its rationality. By revealing the potential of VL representation, we expect the community to divert more attention to VL tracking and hope to open more possibilities for future tracking with diversified multimodal messages.

Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. To date, the dominant methods are CNN-based, leaving plenty of room for improvement. In this work, we propose TransFlow, a transformer architecture for optical flow estimation. Compared to dominant CNN-based methods, TransFlow demonstrates three advantages. First, it provides more accurate correlation and trustworthy matching in flow estimation by utilizing spatial self-attention and cross-attention mechanisms between adjacent frames to effectively capture global dependencies; Second, it recovers more compromised information (e.g., occlusion and motion blur) in flow estimation through long-range temporal association in dynamic scenes; Third, it introduces a concise self-learning paradigm, eliminating the need for complex and laborious multi-stage pre-training procedures. The versatility and superiority of TransFlow extend seamlessly to 3D scene motion, yielding competitive outcomes in 3D scene flow estimation. Our approach attains state-of-the-art results on benchmark datasets such as Sintel and KITTI-15, while also exhibiting exceptional performance on downstream tasks, including video object detection using the ImageNet VID dataset, video frame interpolation using the GoPro dataset, and video stabilization using the DeepStab dataset. We believe that the effectiveness of TransFlow positions it as a flexible baseline for both optical flow and scene flow estimation, offering promising avenues for future research and development.

Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. However, they neglect the relationship between multiple granularities and different features in alignment, degrading detection. Addressing this, we introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning. The key is to encode the dependencies across different granularities including pixel-, instance-, and category-levels simultaneously to align two domains. Specifically, based on pixel-level features, we first develop an omni-scale gated fusion (OSGF) module to aggregate discriminative representations of instances with scale-aware convolutions, leading to robust multi-scale detection. Besides, we introduce multi-granularity discriminators to identify where, either source or target domains, different granularities of samples come from. Note that, MGA not only leverages instance discriminability in different categories but also exploits category consistency between two domains for detection. Furthermore, we present an adaptive exponential moving average (AEMA) strategy that explores model assessments for model update to improve pseudo labels and alleviate local misalignment problem, boosting detection robustness. Extensive experiments on multiple domain adaption scenarios validate the superiority of MGA over other approaches on FCOS and Faster R-CNN detectors.

This paper presents a publicly accessible large-scale geo-tagged Twitter dataset, comprising 95.8 million tweets from 247 countries, spanning from Jan. 2012 to Dec. 2021. To systematically extract this dataset from over 57.18 TB of raw tweets, we employed parallel computing on a 40-node cluster with 480 CPU cores. Distinguishing it from most existing Twitter datasets, our dataset includes four-level granularity tweet locations, two-level granularity user profile locations, and tweet text languages, enabling personalized queries. To enhance the open accessibility of our dataset, we have designed an innovative interactive online query system (https://sigspatial.yunhefeng.me) and provided free-to-use JSON APIs (https://github.com/ResponsibleAILab/unt-geotweet-api) for customized queries to retrieve tweet IDs in tweet coordinate, tweet text-based location, and user location modes. Then users can use https://github.com/ResponsibleAILab/unt-tweet-rehydration to download complete tweet information. Furthermore, we have demonstrated the practical utility of our dataset through two applications: human movement modeling and geo-aware Large Language Model (LLM) tuning. Our geo-tagged Twitter dataset, along with the accompanying query system and APIs, contributes to the research community and opens up avenues for multidisciplinary investigations and the advancement of knowledge.

Current arbitrary style transfer models are limited to either image or video domains. In order to achieve satisfying image and video style transfers, two different models are inevitably required with separate training processes on image and video domains, respectively. In this paper, we show that this can be precluded by introducing UniST, a Unified Style Transfer framework for both images and videos. At the core of UniST is a domain interaction transformer (DIT ), which first explores context information within the specific domain and then interacts contextualized domain information for joint learning. In particular, DIT enables exploration of temporal information from videos for the image style transfer task and meanwhile allows rich appearance texture from images for video style transfer, thus leading to mutual benefits. Considering heavy computation of traditional multi-head self-attention, we present a simple yet effective axial multi-head self-attention (AMSA) for DIT , which improves computational efficiency while maintains style transfer performance. To verify the effectiveness of UniST, we conduct extensive experiments on both image and video style transfer tasks and show that UniST performs favorably against state-of-the-art approaches on both tasks. Code is available at https://github.com/NevSNev/UniST.

Planar object tracking is a critical computer vision problem and has drawn increasing interest owing to its key roles in robotics, augmented reality, etc. Despite rapid progress, its further development, especially in the deep learning era, is largely hindered due to the lack of large-scale challenging benchmarks. Addressing this, we introduce PlanarTrack, a large-scale challenging planar tracking benchmark. Specifically, PlanarTrack consists of 1,000 videos with more than 490K images. All these sequences are collected in complex unconstrained scenarios from the wild, which makes PlanarTrack, compared with existing benchmarks, more challenging but realistic for real-world applications. To ensure the high-quality annotation, each frame in PlanarTrack is manually labeled using four corners with multiple-round careful inspection and refinement. To our best knowledge, PlanarTrack, to date, is the largest and the most challenging dataset dedicated to planar object tracking. In order to analyze the proposed PlanarTrack, we evaluate 10 planar trackers and conduct comprehensive comparisons and in-depth analysis. Our results, not surprisingly, demonstrate that current top-performing planar trackers degenerate significantly on the challenging PlanarTrack and more efforts are needed to improve planar tracking in the future. In addition, we further derive a variant named PlanarTrackBBfor generic object tracking from our PlanarTrack. Our evaluation of 10 excellent generic trackers on PlanarTrackBBmanifests that, surprisingly, PlanarTrackBBis even more challenging than several popular generic tracking benchmarks and more attention should be paid to handle such planar objects, though they are rigid. All benchmarks and evaluations are released at https://hengfan2010.github.io/projects/PlanarTrack/.

Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame sampling may ignore key information in videos and thus degrade performance. Additionally, redundant information in the sampled frames may result in low efficiency in the inference of video captioning. Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed. We propose a simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning. We show that even with a simple design, our method can achieve state-of-the-art performance on different benchmarks while running almost 2× faster than existing approaches. Code is available at https://github.com/acherstyx/CoCap.

Domain adaptive detection aims to improve the generality of a detector, learned from the labeled source domain, on the unlabeled target domain. In this work, drawing inspiration from the concept of stability from the control theory that a robust system requires to remain consistent both externally and internally regardless of disturbances, we propose a novel framework that achieves unsupervised domain adaptive detection through stability analysis. In specific, we treat discrepancies between images and regions from different domains as disturbances, and introduce a novel simple but effective Network Stability Analysis (NSA) framework that considers various disturbances for domain adaptation. Particularly, we explore three types of perturbations including heavy and light image-level disturbances and instance-level disturbance. For each type, NSA performs external consistency analysis on the outputs from raw and perturbed images and/or internal consistency analysis on their features, using teacher-student models. By integrating NSA into Faster R-CNN, we immediately achieve state-of-the-art results. In particular, we set a new record of 52.7% mAP on Cityscapes-to-FoggyCityscapes, showing the potential of NSA for domain adaptive detection. It is worth noticing, our NSA is designed for general purpose, and thus applicable to one-stage detection model (e.g., FCOS) besides the adopted one, as shown by experiments. Code is released at https://github.com/tiankongzhang/NSA.

We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. Having observed de facto frameworks perform feature matching simply using the backbone outputs for target localization, there is no direct feedback from the matching module to the backbone network, especially the shallow layers. Concretely, only the matching module can directly access the target information, while the representation learning of candidate frame is blind to the reference target. Therefore, the accumulated target-irrelevant interference in shallow stages may degrade the feature quality of deeper layers. In this paper, we approach the problem by conducting multiple branch-wise interactions inside the Siamese-like backbone networks (InBN). The core of InBN is a general interaction modeler (GIM) that injects the target information to different stages of the backbone network, leading to better target-perception of candidate feature representation with negligible computation cost. The proposed GIM module and InBN mechanism are general and applicable to different backbone types including CNN and Transformer for improvements, as evidenced on multiple benchmarks. In particular, the CNN version improves the baseline with 3.2/6.9 absolute gains of SUC on LaSOT/TNL2K. The Transformer version obtains SUC of 65.7/52.0 on LaSOT/TNL2K, which are on par with recent SOTAs.

Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training period, making tracking increasingly expensive. In this paper, we demonstrate that the Transformer-reliance is not necessary and the pure ConvNets are still competitive and even better yet more economical and friendly in achieving SOTA tracking. Our solution is to unleash the power of multimodal vision-language (VL) tracking, simply using ConvNets. The essence lies in learning novel unified-adaptive VL representations with our modality mixer (ModaMixer) and asymmetrical ConvNet search. We show that our unified-adaptive VL representation, learned purely with the ConvNets, is a simple yet strong alternative to Transformer visual features, by unbelievably improving a CNN-based Siamese tracker by 14.5% in SUC on challenging LaSOT (50.7%$\rightarrow$65.2%), even outperforming several Transformer-based SOTA trackers. Besides empirical results, we theoretically analyze our approach to evidence its effectiveness. By revealing the potential of VL representation, we expect the community to divert more attention to VL tracking and hope to open more possibilities for future tracking beyond Transformer. Code and models are released at https://github.com/JudasDie/SOTS.

Recently Transformer has been largely explored in tracking and shown state-of-the-art (SOTA) performance. However, existing efforts mainly focus on fusing and enhancing features generated by convolutional neural networks (CNNs). The potential of Transformer in representation learning remains under-explored. In this paper, we aim to further unleash the power of Transformer by proposing a simple yet efficient fully-attentional tracker, dubbed SwinTrack, within classic Siamese framework. In particular, both representation learning and feature fusion in SwinTrack leverage the Transformer architecture, enabling better feature interactions for tracking than pure CNN or hybrid CNN-Transformer frameworks. Besides, to further enhance robustness, we present a novel motion token that embeds historical target trajectory to improve tracking by providing temporal context. Our motion token is lightweight with negligible computation but brings clear gains. In our thorough experiments, SwinTrack exceeds existing approaches on multiple benchmarks. Particularly, on the challenging LaSOT, SwinTrack sets a new record with 0.713 SUC score. It also achieves SOTA results on other benchmarks. We expect SwinTrack to serve as a solid baseline for Transformer tracking and facilitate future research. Our codes and results are released at https://github.com/LitingLin/SwinTrack.

Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset.

Visual tracking has achieved considerable progress in recent years. However, current research in the field mainly focuses on tracking of opaque objects, while little attention is paid to transparent object tracking. In this paper, we make the first attempt in exploring this problem by proposing a Transparent Object Tracking Benchmark (TOTB). Specifically, TOTB consists of 225 videos (86K frames) from 15 diverse transparent object categories. Each sequence is manually labeled with axis-aligned bounding boxes. To the best of our knowledge, TOTB is the first benchmark dedicated to transparent object tracking. In order to understand how existing trackers perform and to provide comparison for future research on TOTB, we extensively evaluate 25 state-of-the-art tracking algorithms. The evaluation results exhibit that more efforts are needed to improve transparent object tracking. Besides, we observe some nontrivial findings from the evaluation that are discrepant with some common beliefs in opaque object tracking. For example, we find that deeper features are not always good for improvements. Moreover, to encourage future research, we introduce a novel tracker, named TransATOM, which leverages transparency features for tracking and surpasses all 25 evaluated approaches by a large margin. By releasing TOTB, we expect to facilitate future research and application of transparent object tracking in both the academia and industry. The TOTB and evaluation results as well as TransATOM are available at https: //hengfan2010.github.io/projects/TOTB/.

High quality object proposals are crucial in visual tracking algorithms that utilize region proposal network (RPN). Refinement of these proposals, typically by box regression and classification in parallel, has been popularly adopted to boost tracking performance. However, it still meets problems when dealing with complex and dynamic background. Thus motivated, in this paper we introduce an improved proposal refinement module, Cascaded Regression-Align-Classification (CRAC), which yields new state-of-the-art performances on many benchmarks.First, having observed that the offsets from box regression can serve as guidance for proposal feature refinement, we design CRAC as a cascade of box regression, feature alignment and box classification. The key is to bridge box regression and classification via an alignment step, which leads to more accurate features for proposal classification with improved robustness. To address the variation in object appearance, we introduce an identification-discrimination component for box classification, which leverages offline reliable fine-grained template and online rich background information to distinguish the target from background. Moreover, we present pyramid RoIAlign that benefits CRAC by exploiting both the local and global cues of proposals. During inference, tracking proceeds by ranking all refined proposals and selecting the best one. In experiments on seven benchmarks including OTB-2015, UAV123, NfS, VOT-2018, TrackingNet, GOT-10k and LaSOT, our CRACT exhibits very promising results in comparison with state-of-the-art competitors and runs in real-time at 28 fps.

Generic visual object tracking is difficult due to many challenge factors (e.g., occlusion, blur, etc.). Each of these factors may cause serious problems for a tracker, and when they work together can make things even more complicated. Despite a great amount of efforts devoted to understanding the behavior of trackers, reliable and quantifiable ways for studying the per factor tracking behavior remain barely available. Addressing this issue, in this paper we contribute to the community a tracking diagnosis toolkit, TracKlinic, for diagnosis of challenge factors of tracking algorithms.TracKlinic consists of two novel components focusing on the data and analysis aspects, respectively. For the data component, we carefully prepare a set of 2,390 annotated videos, each involving one and only one major challenge factor. When analyzing an algorithm for a specific challenge factor, such one-factor-per-sequence rule greatly inhibits the disturbance from other factors and consequently leads to more faithful analysis. For the analysis component, given the tracking results on all sequences, it investigates the behavior of the tracker under each individual factor and generates the report automatically. With TracKlinic, a thorough study is conducted on ten state-of-the-art trackers on nine challenge factors (including two compound ones). The results suggest that, heavy shape variation and occlusion are the two most challenging factors faced by most trackers. Besides, out-of-view, though does not happen frequently, is often fatal. By sharing TracKlinic1, we expect to make it much easier for diagnosing tracking algorithms, and to thus facilitate developing better ones.

We introduce MART, Motion-Aware Recurrent neural network (MA-RNN) for Tracking, by modeling robust long-term spatial-temporal representation. In particular, we propose a simple, yet effective context-aware displacement attention (CADA) module to capture target motion in videos. By seamlessly integrating CADA into RNN, the proposed MA-RNN can spatially align and aggregate temporal information guided by motion from frame to frame, leading to more effective representation that benefits a tracker from motion when handling occlusion, deformation, viewpoint change etc. Moreover, to deal with scale change, we present a monotonic bounding box regression (mBBR) approach that iteratively predicts regression offsets for target object under the guidance of intersection-over-union (IoU) score, guaranteeing non-decreasing accuracy. In extensive experiments on five benchmarks, including GOT-10k, LaSOT, TC-128, OTB-15 and VOT-19, our tracker MART consistently achieves state-of-the-art results and runs in real-time.

Spatial misalignment caused by variations in poses and viewpoints is one of the most critical issues that hinder the performance improvement in existing person re-identification (Re-ID) algorithms. Although it is straightforward to explore correspondence learning algorithms for alignment, online learning is intractable for negative pairs due to the intrinsic visual difference between negative pairs and efficiency concern. To address this problem, in this paper, we present a robust and efficient graph correspondence transfer (REGCT) approach for explicit spatial alignment in Re-ID. Specifically, we propose the off-line correspondence learning and on-line correspondence transfer framework. During training, patch-wise correspondences between positive training pairs are established via graph matching. By exploiting both spatial and visual contexts of human appearance in graph matching, meaningful semantic correspondences can be obtained. During testing, the off-line learned patch-wise correspondence templates are transferred to test pairs with similar pose-pair configurations for local feature distance calculation. To enhance the robustness of correspondence transfer, we design a novel pose context descriptor to accurately model human body configurations, and present an approach to measure the similarity between a pair of pose context descriptors. Meanwhile, to improve testing efficiency, we propose a correspondence template ensemble method using the voting mechanism, which significantly reduces the amount of patch-wise matchings involved in distance calculation. With the aforementioned strategies, the REGCT model can effectively and efficiently handle the spatial misalignment problem in Re-ID. Extensive experiments on five challenging benchmarks, including VIPeR, Road, PRID450S, 3DPES, and CUHK01, evidence the superior performance of REGCT over other state-of-the-art approaches.

Recently, the region proposal networks (RPN) have been combined with the Siamese network for tracking, and shown excellent accuracy with high efficiency. Nevertheless, previously proposed one-stage Siamese-RPN trackers degenerate in presence of similar distractors and large scale variation. Addressing these issues, we propose a multi-stage tracking framework, Siamese Cascaded RPN (C-RPN), which consists of a sequence of RPNs cascaded from deep high-level to shallow low-level layers in a Siamese network. Compared to previous solutions, C-RPN has several advantages: (1) Each RPN is trained using the outputs of RPN in the previous stage. Such process stimulates hard negative sampling, resulting in more balanced training samples. Consequently, the RPNs are sequentially more discriminative in distinguishing difficult background (i.e.,, similar distractors). (2) Multi-level features are fully leveraged through a novel feature transfer block (FTB) for each RPN, further improving the discriminability of C-RPN using both high-level semantic and low-level spatial information. (3) With multiple steps of regressions, C-RPN progressively refines the location and shape of the target in each RPN with adjusted anchor boxes in the previous stage, which makes localization more accurate. C-RPN is trained end-to-end with the multi-task loss function. In inference, C-RPN is deployed as it is, without any temporal adaption, for real-time tracking. In extensive experiments on OTB-2013, OTB-2015, VOT-2016, VOT-2017, LaSOT and TrackingNet, C-RPN consistently achieves state-of-the-art results and runs in real-time.

In this paper, we present LaSOT, a high-quality benchmark for Large-scale Single Object Tracking. LaSOT consists of 1,400 sequences with more than 3.5M frames in total. Each frame in these sequences is carefully and manually annotated with a bounding box, making LaSOT the largest, to the best of our knowledge, densely annotated tracking benchmark. The average video length of LaSOT is more than 2,500 frames, and each sequence comprises various challenges deriving from the wild where target objects may disappear and re-appear again in the view. By releasing LaSOT, we expect to provide the community with a large-scale dedicated benchmark with high quality for both the training of deep trackers and the veritable evaluation of tracking algorithms. Moreover, considering the close connections of visual appearance and natural language, we enrich LaSOT by providing additional language specification, aiming at encouraging the exploration of natural linguistic feature for tracking. A thorough experimental evaluation of 35 tracking algorithms on LaSOT is presented with detailed analysis, and the results demonstrate that there is still a big room for improvements.

In this paper, we propose the novel complementary Siamese networks (CoSNet) for visual tracking by exploiting complementary global and local representations to learn a matching function. In specific, the proposed CoSNet is two-fold: a global Siamese network (GSNet) and a local Siamese network (LSNet). The GSNet aims to match the target with candidates using holistic representation. By contrast, the LSNet explores partial object representation for matching. Instead of simply decomposing the object into regular patches in LSNet, we propose a novel attentional local part network, which automatically generates salient object parts for local representation and adaptively weights each part according to its importance in matching. In CoSNet, the GSNet and LSNet are jointly trained in an end-to-end manner. By coupling two complementary Siamese networks, our CoSNet learns a robust matching function which can effectively handle various appearance changes in visual tracking. Extensive experiments on a large-scale dataset with 100 sequences show that CoSNet outperforms other state-of-the-art trackers.

Detecting objects in aerial images is challenging for at least two reasons: (1) target objects like pedestrians are very small in pixels, making them hardly distinguished from surrounding background; and (2) targets are in general sparsely and non-uniformly distributed, making the detection very inefficient. In this paper, we address both issues inspired by observing that these targets are often clustered. In particular, we propose a Clustered Detection (ClusDet) network that unifies object clustering and detection in an end-to-end framework. The key components in ClusDet include a cluster proposal sub-network (CPNet), a scale estimation sub-network (ScaleNet), and a dedicated detection network (DetecNet). Given an input image, CPNet produces object cluster regions and ScaleNet estimates object scales for these regions. Then, each scale-normalized cluster region is fed into DetecNet for object detection. ClusDet has several advantages over previous solutions: (1) it greatly reduces the number of chips for final object detection and hence achieves high running time efficiency, (2) the cluster-based scale estimation is more accurate than previously used single-object based ones, hence effectively improves the detection for small objects, and (3) the final DetecNet is dedicated for clustered regions and implicitly models the prior context information so as to boost detection accuracy. The proposed method is tested on three popular aerial image datasets including VisDrone, UAVDT and DOTA. In all experiments, ClusDet achieves promising performance in comparison with state-of-the-art detectors.

Deep learning has powered many face related tasks and shown state-of-the-art performance. However, existing deep models are often trained separately for different problems, which results in heavy computational burden. To address this problem, we propose a novel multi-task network with fully convolutional architecture-Hierarchical Multi-task Network (HMT-Net), that simultaneously recognizes a person's gender, race and facial attractiveness from a given portrait image. Aiming to improve the robustness to outliers in facial beauty prediction task, a novel loss is introduced into HMTNet. Compared to existing deep approaches, the proposed HMTNet achieves state-of-the-art performance on several datasets, and it can learn more discriminative feature representation through joint training and feature aggregation. Extensive experiments evidence the effectiveness of HMTNet.

Recent progresses in model-free single object tracking (SOT) algorithms have largely inspired applying SOT to multi-object tracking (MOT) to improve the robustness as well as relieving dependency on external detector. However, SOT algorithms are generally designed for distinguishing a target from its environment, and hence meet problems when a target is spatially mixed with similar objects as observed frequently in MOT. To address this issue, in this paper we propose an instance-aware tracker to integrate SOT techniques for MOT by encoding awareness both within and between target models. In particular, we construct each target model by fusing information for distinguishing target both from background and other instances (tracking targets). To conserve uniqueness of all target models, our instance-aware tracker considers response maps from all target models and assigns spatial locations exclusively to optimize the overall accuracy. Another contribution we make is a dynamic model refreshing strategy learned by a convolutional neural network. This strategy helps to eliminate initialization noise as well as to adapt to variation of target size and appearance. To show the effectiveness of the proposed approach, it is evaluated on the popular MOT15 and MOT16 challenge benchmarks. On both benchmarks, our approach achieves the best overall performances in comparison with published results.

Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic dependencies among image units. Different from existing RNN based approaches, our dense RNNs are able to capture richer contextual dependencies for each image unit by enabling immediate connections between each pair of image units, which significantly enhances their discriminative power. Besides, to select relevant dependencies and meanwhile to restrain irrelevant ones for each unit from dense connections, we introduce an attention model into dense RNNs. The attention model allows automatically assigning more importance to helpful dependencies while less weight to unconcerned dependencies. Integrating with convolutional neural networks (CNNs), we develop an end-to-end scene labeling system. Extensive experiments on three large-scale benchmarks demonstrate that the proposed approach can improve the baselines by large margins and outperform other state-of-the-art algorithms.

Visual object tracking has played a crucial role in computer vision with many applications. Being intensively studied in recent decades, visual tracking has witnessed great advances in either speed (e.g., with correlation filters) or accuracy (e.g., with deep features). Real-time and high accuracy tracking algorithms, nevertheless, remain scarce. In this paper we study the problem from a new perspective and present a novel parallel tracking and verifying (PTAV) framework, by taking advantage of the ubiquity of multi-thread techniques and borrowing ideas from the success of parallel tracking and mapping in visual SLAM. The proposed PTAV framework typically consists of two components, a (base) tracker T and a verifier V, working in parallel on two separate threads. The tracker T aims at providing a super real-time tracking inference and is expected to perform well most of the time; by contrast, the verifier V validates the tracking results and corrects T when needed. The key innovation is that, V does not work on every frame but only upon the requests from T; on the other end, T may adjust the tracking according to the feedback from V. With such collaboration, PTAV enjoys both high efficiency provided by T and strong discriminative power by V. Meanwhile, in order to adapt V to object appearance changes, we maintain a dynamic target template pool for adaptive verification, resulting in further improvement. In our extensive experiments on OTB2015, TC128, UAV20L and VOT2016, PTAV achieves top tracking accuracy among all real-time trackers, and in fact even outperforms many deep learning based algorithms. Moreover, as a general framework, PTAV is very flexible with great potentials for future improvement and generalization.

In this paper, we propose a graph correspondence transfer (GCT) approach for person re-identification. Unlike existing methods, the GCT model formulates person re-identification as an off-line graph matching and on-line correspondence transferring problem. In specific, during training, the GCT model aims to learn off-line a set of correspondence templates from positive training pairs with various pose-pair configurations via patch-wise graph matching. During testing, for each pair of test samples, we select a few training pairs with the most similar pose-pair configurations as references, and transfer the correspondences of these references to test pair for feature distance calculation. The matching score is derived by aggregating distances from different references. For each probe image, the gallery image with the highest matching score is the re-identifying result. Compared to existing algorithms, our GCT can handle spatial misalignment caused by large variations in view angles and human poses owing to the benefits of patch-wise graph matching. Extensive experiments on five benchmarks including VIPeR, Road, PRID450S, 3DPES and CUHK01 evidence the superior performance of GCT model over other state-of-the-art methods.

Image context in image is crucial for improving scene labeling. While the existing methods only exploit local context generated from a small surrounding area of an image patch or a pixel, the long-range and global contextual information is often ignored. To handle this issue, we propose a novel approach for scene labeling by multi-level contextual recurrent neural networks (RNNs). We encode three kinds of contextual cues, viz., local context, global context, and image topic context in structural RNNs to model long-range local and global dependencies in an image. In this way, our method is able to “see” the image in terms of both long-range local and holistic views, and make a more reliable inference for image labeling. Besides, we integrate the proposed contextual RNNs into hierarchical convolutional neural networks, and exploit dependence relationships at multiple levels to provide rich spatial and semantic information. Moreover, we adopt an attention model to effectively merge multiple levels and show that it outperforms average- or max-pooling fusion strategies. Extensive experiments demonstrate that the proposed approach achieves improved results on the CamVid, KITTI, SiftFlow, Stanford Background, and Cityscapes data sets.

Correlation filter has drawn increasing interest in visual tracking due to its high efficiency, however, it is sensitive to partial occlusion, which may result in tracking failure. To address this problem, we propose a novel local-global correlation filter (LGCF) for object tracking. Our LGCF model utilizes both local-based and global-based strategies, and effectively combines these two strategies by exploiting the relationship of circular shifts among local object parts and global target for their motion models to preserve the structure of object. In specific, our proposed model has two advantages: (1) Owing to the benefits of local-based mechanism, our method is robust to partial occlusion by leveraging visible parts. (2) Taking into account the relationship of motion models among local parts and global target, our LGCF model is able to capture the inner structure of object, which further improves its robustness to occlusion. In addition, to alleviate the issue of drift away from object, we incorporate temporal consistencies of both local parts and global target in our LGCF model. Besides, we adopt an adaptive method to accurately estimate the scale of object. Extensive experiments on OTB15 with 100 videos demonstrate that our tracking algorithm performs favorably against state-of-the-art methods.

In this paper, we exploit deep convolutional features for object appearance modeling and propose a simple while effective deep discriminative model (DDM) for visual tracking. The proposed DDM takes as input the deep features and outputs an object-background confidence map. Considering that both spatial information from lower convolutional layers and semantic information from higher layers benefit object tracking, we construct multiple deep discriminative models (DDMs) for each layer and combine these confidence maps from each layer to obtain the final object-background confidence map. To reduce the risk of model drift, we propose to adopt a saliency method to generate object candidates. Object tracking is then achieved by finding the candidate with the largest confidence value. Experiments on a large-scale tracking benchmark demonstrate that the propose method performs favorably against state-of-the-art trackers.

Being intensively studied, visual tracking has seen great recent advances in either speed (e.g., with correlation filters) or accuracy (e.g., with deep features). Real-time and high accuracy tracking algorithms, however, remain scarce. In this paper we study the problem from a new perspective and present a novel parallel tracking and verifying (PTAV) framework, by taking advantage of the ubiquity of multithread techniques and borrowing from the success of parallel tracking and mapping in visual SLAM. Our PTAV framework typically consists of two components, a tracker T and a verifier V, working in parallel on two separate threads. The tracker T aims to provide a super real-time tracking inference and is expected to perform well most of the time; by contrast, the verifier V checks the tracking results and corrects T when needed. The key innovation is that, V does not work on every frame but only upon the requests from T; on the other end, T may adjust the tracking according to the feedback from V. With such collaboration, PTAV enjoys both the high efficiency provided by T and the strong discriminative power by V. In our extensive experiments on popular benchmarks including OTB2013, OTB2015, TC128 and UAV20L, PTAV achieves the best tracking accuracy among all real-time trackers, and in fact performs even better than many deep learning based solutions. Moreover, as a general framework, PTAV is very flexible and has great rooms for improvement and generalization.

Skin detection from images, typically used as a preprocessing step, has a wide range of applications such as dermatology diagnostics, human computer interaction designs, and etc. It is a challenging problem due to many factors such as variation in pigment melanin, uneven illumination, and differences in ethnicity geographics. Besides, age and gender introduce additional difficulties to the detection process. It is hard to determine whether a single pixel is skin or nonskin without considering the context. An efficient traditional hand-engineered skin color detection algorithm requires extensive work by domain experts. Recently, deep learning algorithms, especially convolutional neural networks (CNNs), have achieved great success in pixel-wise labeling tasks. However, CNN-based architectures are not sufficient for modeling the relationship between pixels and their neighbors. In this letter, we integrate recurrent neural networks (RNNs) layers into the fully convolutional neural networks (FCNs), and develop an end-to-end network for human skin detection. In particular, FCN layers capture generic local features, while RNN layers model the semantic contextual dependencies in images. Experimental results on the COMPAQ and ECU skin datasets validate the effectiveness of the proposed approach, where RNN layers enhance the discriminative power of skin detection in complex background situations.

Dictionary learning for sparse representation has been increasingly applied to object tracking, however, the existing methods only utilize one modality of the object to learn a single dictionary. In this paper, we propose a robust tracking method based on multitask joint dictionary learning. Through extracting different features of the target, multiple linear sparse representations are obtained. Each sparse representation can be learned by a corresponding dictionary. Instead of separately learning the multiple dictionaries, we adopt a multitask learning approach to learn the multiple linear sparse representations, which provide additional useful information to the classification problem. Because different tasks may favor different sparse representation coefficients, yet the joint sparsity may enforce the robustness in coefficient estimation. During tracking, a classifier is constructed based on a joint linear representation, and the candidate with the smallest joint decision error is selected to be the tracked object. In addition, reliable tracking results and augmented training samples are accumulated into two sets to update the dictionaries for classification, which helps our tracker adapt to the fast time-varying object appearance. Both qualitative and quantitative evaluations on CVPR2013 visual tracking benchmark demonstrate that our method performs favorably against state-of-the-art trackers.

In this paper, we propose a vision-based approach for roadside vegetation detection by superpixel matching with local context. Unlike previous detection methods which seek help from additional sensors such as lidar, our algorithm only requires an off-the-shelf camera. The proposed method contains two stages. In the first stage, a superpixel database is constructed by segmenting training images into superpixels, and each superpixel patch is represented with multiple features. After that, the appearance information of vegetation or non-vegetation is encoded in the superpixel database. In the second stage, vegetation detection in each testing image is achieved by superpixel matching. The test image is segmented into superpixels and the (vegetation) label cost of each superpixel is derived by comparing with the k-nearest neighbors in the superpixel database. Furthermore, we incorporate the local context information through the feedback to refine superpixel matching. Taking this context information into account, Markov Random Field (MRF) is utilized to further improve the classification accuracy. Besides, considering the stable layout of road scene images, we utilize spatial priors of road scene to guide vegetation classification. Experiments on real-world datasets demonstrate the promise of our method.