This paper presents enhancements to the SAM2 framework for video object tracking task, addressing challenges such as occlusions, background clutter, and target reappearance. We introduce a hierarchical motion estimation strategy, combining lightweight linear prediction with selective non-linear refinement to improve tracking accuracy without requiring additional training. In addition, we optimize the memory bank by distinguishing long-term and short-term memory frames, enabling more reliable tracking under long-term occlusions and appearance changes. Experimental results show consistent improvements across different model scales. Our method achieves state-of-the-art performance on LaSOT and LaSOText with the large model, achieving 9.6% and 7.2% relative improvements in AUC over the original SAM2, and demonstrates even larger relative gains on smaller models, highlighting the effectiveness of our trainless, low-overhead improvements for boosting long-term tracking performance. The code is available at https://github.com/LouisFinner/HiM2SAM.
Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while efficient, neglect the value of direct involvement of multiple reference frames for reconstruction and decision-making aspects, especially in complex situations such as occlusion or fast movement. In this paper, we introduce a Dynamic Memory Prediction (DMP) framework that innovatively utilizes multiple reference frames to concisely and directly enhance frame reconstruction. Its core component is a Reference Frame Memory Engine that dynamically selects frames based on object pixel features to improve tracking accuracy. In addition, a Bidirectional Target Prediction Network is built to utilize multiple reference frames to improve the robustness of the model. Through experiments, our algorithm outperforms the state-of-the-art self-supervised techniques on two fine-grained video object tracking tasks: object segmentation and keypoint tracking.
Multimodal tracking has garnered widespread attention as a result of its ability to effectively address the inherent limitations of traditional RGB tracking. However, existing multimodal trackers mainly focus on the fusion and enhancement of spatial features or merely leverage the sparse temporal relationships between video frames. These approaches do not fully exploit the temporal correlations in multimodal videos, making it difficult to capture the dynamic changes and motion information of targets in complex scenarios. To alleviate this problem, we propose a unified multimodal spatial-temporal tracking approach named STTrack. In contrast to previous paradigms that solely relied on updating reference information, we introduced a temporal state generator (TSG) that continuously generates a sequence of tokens containing multimodal temporal information. These temporal information tokens are used to guide the localization of the target in the next time state, establish long-range contextual relationships between video frames, and capture the temporal trajectory of the target. Furthermore, at the spatial level, we introduced the mamba fusion and background suppression interactive (BSI) modules. These modules establish a dual-stage mechanism for coordinating information interaction and fusion between modalities. Extensive comparisons on five benchmark datasets illustrate that STTrack achieves state-of-the-art performance across various multimodal tracking scenarios. Code is available at: https://github.com/NJU-PCALab/STTrack.
Contextual information at the video level has become increasingly crucial for visual object tracking. However, existing methods typically use only a few tokens to convey this information, which can lead to information loss and limit their ability to fully capture the context. To address this issue, we propose a new video-level visual object tracking framework called MCITrack. It leverages Mamba's hidden states to continuously record and transmit extensive contextual information throughout the video stream, resulting in more robust object tracking. The core component of MCITrack is the Contextual Information Fusion module, which consists of the mamba layer and the cross-attention layer. The mamba layer stores historical contextual information, while the cross-attention layer integrates this information into the current visual features of each backbone block. This module enhances the model's ability to capture and utilize contextual information at multiple levels through deep integration with the backbone. Experiments demonstrate that MCITrack achieves competitive performance across numerous benchmarks. For instance, it gets 76.6% AUC on LaSOT and 80.0% AO on GOT-10k, establishing a new state-of-the-art performance. Code and models are available at https://github.com/kangben258/MCITrack.
Referring video object segmentation (RVOS) requires tracking and segmenting an object throughout a video according to a given natural language expression, demanding both complex motion understanding and the alignment of visual representations with language descriptions. Given these challenges, the recently proposed Segment Anything Model 2 (SAM2) emerges as a potential candidate due to its ability to generate coherent segmentation mask tracks across video frames, and provide an inherent spatio-temporal objectness in its object token representations. In this paper, we introduce SOLA (Selection by Object Language Alignment), a novel framework that leverages SAM2 object tokens as compact video-level object representations, which are aligned with language features through a lightweight track selection module. To effectively facilitate this alignment, we propose an IoU-based pseudo-labeling strategy, which bridges the modality gap between SAM2 representations with language features. Extensive experiments show that SOLA achieves state-of-the-art performance on the MeViS dataset and demonstrate that SOLA offers an effective solution for RVOS. Our project page is available at: https://cvlab-kaist.github.io/SOLA.
Vision-Language Models (VLMs) have shown remarkable capabilities across diverse visual tasks, including image recognition, video understanding, and Visual Question Answering (VQA) when explicitly trained for these tasks. Despite these advances, we find that current VLMs lack a fundamental cognitive ability: learning to localize objects in a scene by taking into account the context. In this work, we focus on the task of few-shot personalized localization, where a model is given a small set of annotated images (in-context examples) -- each with a category label and bounding box -- and is tasked with localizing the same object type in a query image. To provoke personalized localization abilities in models, we present a data-centric solution that fine-tunes them using carefully curated data from video object tracking datasets. By leveraging sequences of frames tracking the same object across multiple shots, we simulate instruction-tuning dialogues that promote context awareness. To reinforce this, we introduce a novel regularization technique that replaces object labels with pseudo-names, ensuring the model relies on visual context rather than prior knowledge. Our method significantly enhances few-shot localization performance without sacrificing generalization, as demonstrated on several benchmarks tailored to personalized localization. This work is the first to explore and benchmark personalized few-shot localization for VLMs, laying a foundation for future research in context-driven vision-language applications. The code for our project is available at https://github.com/SivanDoveh/IPLoc
RGB video object tracking is a fundamental task in computer vision. Its effectiveness can be improved using depth information, particularly for handling motion-blurred target. However, depth information is often missing in commonly used tracking benchmarks. In this work, we propose a new framework that leverages monocular depth estimation to counter the challenges of tracking targets that are out of view or affected by motion blur in RGB video sequences. Specifically, our work introduces following contributions. To the best of our knowledge, we are the first to propose a depth attention mechanism and to formulate a simple framework that allows seamlessly integration of depth information with state of the art tracking algorithms, without RGB-D cameras, elevating accuracy and robustness. We provide extensive experiments on six challenging tracking benchmarks. Our results demonstrate that our approach provides consistent gains over several strong baselines and achieves new SOTA performance. We believe that our method will open up new possibilities for more sophisticated VOT solutions in real-world scenarios. Our code and models are publicly released: https://github.com/LiuYuML/Depth-Attention.
Many current visual object tracking benchmarks such as OTB100, NfS, UAV123, LaSOT, and GOT-10K, predominantly contain day-time scenarios while the challenges posed by the night-time has been less investigated. It is primarily because of the lack of a large-scale, well-annotated night-time benchmark for rigorously evaluating tracking algorithms. To this end, this paper presents NT-VOT211, a new benchmark tailored for evaluating visual object tracking algorithms in the challenging night-time conditions. NT-VOT211 consists of 211 diverse videos, offering 211,000 well-annotated frames with 8 attributes including camera motion, deformation, fast motion, motion blur, tiny target, distractors, occlusion and out-of-view. To the best of our knowledge, it is the largest night-time tracking benchmark to-date that is specifically designed to address unique challenges such as adverse visibility, image blur, and distractors inherent to night-time tracking scenarios. Through a comprehensive analysis of results obtained from 42 diverse tracking algorithms on NT-VOT211, we uncover the strengths and limitations of these algorithms, highlighting opportunities for enhancements in visual object tracking, particularly in environments with suboptimal lighting. Besides, a leaderboard for revealing performance rankings, annotation tools, comprehensive meta-information and all the necessary code for reproducibility of results is made publicly available. We believe that our NT-VOT211 benchmark will not only be instrumental in facilitating field deployment of VOT algorithms, but will also help VOT enhancements and it will unlock new real-world tracking applications. Our dataset and other assets can be found at: {https://github.com/LiuYuML/NV-VOT211.
Open-vocabulary multi-object tracking (OVMOT) represents a critical new challenge involving the detection and tracking of diverse object categories in videos, encompassing both seen categories (base classes) and unseen categories (novel classes). This issue amalgamates the complexities of open-vocabulary object detection (OVD) and multi-object tracking (MOT). Existing approaches to OVMOT often merge OVD and MOT methodologies as separate modules, predominantly focusing on the problem through an image-centric lens. In this paper, we propose VOVTrack, a novel method that integrates object states relevant to MOT and video-centric training to address this challenge from a video object tracking standpoint. First, we consider the tracking-related state of the objects during tracking and propose a new prompt-guided attention mechanism for more accurate localization and classification (detection) of the time-varying objects. Subsequently, we leverage raw video data without annotations for training by formulating a self-supervised object similarity learning technique to facilitate temporal object association (tracking). Experimental results underscore that VOVTrack outperforms existing methods, establishing itself as a state-of-the-art solution for open-vocabulary tracking task.
Multi-object tracking (MOT) emerges as a pivotal and highly promising branch in the field of computer vision. Classical closed-vocabulary MOT (CV-MOT) methods aim to track objects of predefined categories. Recently, some open-vocabulary MOT (OV-MOT) methods have successfully addressed the problem of tracking unknown categories. However, we found that the CV-MOT and OV-MOT methods each struggle to excel in the tasks of the other. In this paper, we present a unified framework, Associate Everything Detected (AED), that simultaneously tackles CV-MOT and OV-MOT by integrating with any off-the-shelf detector and supports unknown categories. Different from existing tracking-by-detection MOT methods, AED gets rid of prior knowledge (e.g. motion cues) and relies solely on highly robust feature learning to handle complex trajectories in OV-MOT tasks while keeping excellent performance in CV-MOT tasks. Specifically, we model the association task as a similarity decoding problem and propose a sim-decoder with an association-centric learning mechanism. The sim-decoder calculates similarities in three aspects: spatial, temporal, and cross-clip. Subsequently, association-centric learning leverages these threefold similarities to ensure that the extracted features are appropriate for continuous tracking and robust enough to generalize to unknown categories. Compared with existing powerful OV-MOT and CV-MOT methods, AED achieves superior performance on TAO, SportsMOT, and DanceTrack without any prior knowledge. Our code is available at https://github.com/balabooooo/AED.
Medical image segmentation plays a pivotal role in clinical diagnostics and treatment planning, yet existing models often face challenges in generalization and in handling both 2D and 3D data uniformly. In this paper, we introduce Medical SAM 2 (MedSAM-2), a generalized auto-tracking model for universal 2D and 3D medical image segmentation. The core concept is to leverage the Segment Anything Model 2 (SAM2) pipeline to treat all 2D and 3D medical segmentation tasks as a video object tracking problem. To put it into practice, we propose a novel \emph{self-sorting memory bank} mechanism that dynamically selects informative embeddings based on confidence and dissimilarity, regardless of temporal order. This mechanism not only significantly improves performance in 3D medical image segmentation but also unlocks a \emph{One-Prompt Segmentation} capability for 2D images, allowing segmentation across multiple images from a single prompt without temporal relationships. We evaluated MedSAM-2 on five 2D tasks and nine 3D tasks, including white blood cells, optic cups, retinal vessels, mandibles, coronary arteries, kidney tumors, liver tumors, breast cancer, nasopharynx cancer, vestibular schwannoma, mediastinal lymph nodules, cerebral artery, inferior alveolar nerve, and abdominal organs, comparing it against state-of-the-art (SOTA) models in task-tailored, general and interactive segmentation settings. Our findings demonstrate that MedSAM-2 surpasses a wide range of existing models and updates new SOTA on several benchmarks. The code is released on the project page: https://supermedintel.github.io/Medical-SAM2/.
Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance varies. While a generalist model capable of leveraging all modalities would be ideal, development is hindered by data sparsity, typically in practice, only one modality is available at a time. Therefore, it is crucial to ensure and achieve that knowledge gained from multimodal sensing -- such as identifying relevant features and regions -- is effectively shared, even when certain modalities are unavailable at inference. We venture with a simple assumption: similar samples across different modalities have more knowledge to share than otherwise. To implement this, we employ a ``weak" classifier tasked with distinguishing between modalities. More specifically, if the classifier ``fails" to accurately identify the modality of the given sample, this signals an opportunity for cross-modal knowledge sharing. Intuitively, knowledge transfer is facilitated whenever a sample from one modality is sufficiently close and aligned with another. Technically, we achieve this by routing samples from one modality to the expert of the others, within a mixture-of-experts framework designed for multimodal video object tracking. During the inference, the expert of the respective modality is chosen, which we show to benefit from the multimodal knowledge available during training, thanks to the proposed method. Through the exhaustive experiments that use only paired RGB-E, RGB-D, and RGB-T during training, we showcase the benefit of the proposed method for RGB-X tracker during inference, with an average +3\% precision improvement over the current SOTA. Our source code is publicly available at https://github.com/supertyd/XTrack/tree/main.
We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-agnostic segmentation models. Contrasted to prior 3D scene segmentation approaches that rely on video object tracking or contrastive learning methods, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses through a novel 3D-aware memory bank. By eliminating the assumption of continuous view changes in training images, Gaga demonstrates robustness to variations in camera poses, particularly beneficial for sparsely sampled images, ensuring precise mask label consistency. Furthermore, Gaga accommodates 2D segmentation masks from diverse sources and demonstrates robust performance with different open-world zero-shot class-agnostic segmentation models, significantly enhancing its versatility. Extensive qualitative and quantitative evaluations demonstrate that Gaga performs favorably against state-of-the-art methods, emphasizing its potential for real-world applications such as 3D scene understanding and manipulation.
Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts throughout the entire video, making it hard to handle the different tasks with the same architecture. We make an attempt to address these issues and present a novel unified VS architecture, namely UniVS, by using prompts as queries. UniVS averages the prompt features of the target from previous frames as its initial query to explicitly decode masks, and introduces a target-wise prompt cross-attention layer in the mask decoder to integrate prompt features in the memory pool. By taking the predicted masks of entities from previous frames as their visual prompts, UniVS converts different VS tasks into prompt-guided target segmentation, eliminating the heuristic inter-frame matching process. Our framework not only unifies the different VS tasks but also naturally achieves universal training and testing, ensuring robust performance across different scenarios. UniVS shows a commendable balance between performance and universality on 10 challenging VS benchmarks, covering video instance, semantic, panoptic, object, and referring segmentation tasks. Code can be found at \url{https://github.com/MinghanLi/UniVS}.
Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between reference and search frames via an offline mode. Consequently, they can only interact independently within each image-pair and establish limited temporal correlations. To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named \textbf{ODTrack}, which densely associates the contextual relationships of video frames in an online token propagation manner. ODTrack receives video frames of arbitrary length to capture the spatio-temporal trajectory relationships of an instance, and compresses the discrimination features (localization information) of a target into a token sequence to achieve frame-to-frame association. This new solution brings the following benefits: 1) the purified token sequences can serve as prompts for the inference in the next video frame, whereby past information is leveraged to guide future inference; 2) the complex online update strategies are effectively avoided by the iterative propagation of token sequences, and thus we can achieve more efficient model representation and computation. ODTrack achieves a new \textit{SOTA} performance on seven benchmarks, while running at real-time speed. Code and models are available at \url{https://github.com/GXNU-ZhongLab/ODTrack}.
We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames. Building on the foundation of its predecessor, ARTrackV2 extends the concept by introducing a unified generative framework to "read out" object's trajectory and "retell" its appearance in an autoregressive manner. This approach fosters a time-continuous methodology that models the joint evolution of motion and visual features, guided by previous estimates. Furthermore, ARTrackV2 stands out for its efficiency and simplicity, obviating the less efficient intra-frame autoregression and hand-tuned parameters for appearance updates. Despite its simplicity, ARTrackV2 achieves state-of-the-art performance on prevailing benchmark datasets while demonstrating remarkable efficiency improvement. In particular, ARTrackV2 achieves AO score of 79.5\% on GOT-10k, and AUC of 86.1\% on TrackingNet while being $3.6 \times$ faster than ARTrack. The code will be released.
In the realm of video object tracking, auxiliary modalities such as depth, thermal, or event data have emerged as valuable assets to complement the RGB trackers. In practice, most existing RGB trackers learn a single set of parameters to use them across datasets and applications. However, a similar single-model unification for multi-modality tracking presents several challenges. These challenges stem from the inherent heterogeneity of inputs -- each with modality-specific representations, the scarcity of multi-modal datasets, and the absence of all the modalities at all times. In this work, we introduce Un-Track, a Unified Tracker of a single set of parameters for any modality. To handle any modality, our method learns their common latent space through low-rank factorization and reconstruction techniques. More importantly, we use only the RGB-X pairs to learn the common latent space. This unique shared representation seamlessly binds all modalities together, enabling effective unification and accommodating any missing modality, all within a single transformer-based architecture. Our Un-Track achieves +8.1 absolute F-score gain, on the DepthTrack dataset, by introducing only +2.14 (over 21.50) GFLOPs with +6.6M (over 93M) parameters, through a simple yet efficient prompting strategy. Extensive comparisons on five benchmark datasets with different modalities show that Un-Track surpasses both SOTA unified trackers and modality-specific counterparts, validating our effectiveness and practicality. The source code is publicly available at https://github.com/Zongwei97/UnTrack.
In recent years, Video Object Segmentation (VOS) has emerged as a complementary method to Video Object Tracking (VOT). VOS focuses on classifying all the pixels around the target, allowing for precise shape labeling, while VOT primarily focuses on the approximate region where the target might be. However, traditional segmentation modules usually classify pixels frame by frame, disregarding information between adjacent frames. In this paper, we propose a new algorithm that addresses this limitation by analyzing the motion pattern using the inherent tensor structure. The tensor structure, obtained through Tucker2 tensor decomposition, proves to be effective in describing the target's motion. By incorporating this information, we achieved competitive results on Four benchmarks LaSOT\cite{fan2019lasot}, AVisT\cite{noman2022avist}, OTB100\cite{7001050}, and GOT-10k\cite{huang2019got} LaSOT\cite{fan2019lasot} with SOTA. Furthermore, the proposed tracker is capable of real-time operation, adding value to its practical application.
The Associating Objects with Transformers (AOT) framework has exhibited exceptional performance in a wide range of complex scenarios for video object tracking and segmentation. In this study, we convert the bounding boxes to masks in reference frames with the help of the Segment Anything Model (SAM) and Alpha-Refine, and then propagate the masks to the current frame, transforming the task from Video Object Tracking (VOT) to video object segmentation (VOS). Furthermore, we introduce MSDeAOT, a variant of the AOT series that incorporates transformers at multiple feature scales. MSDeAOT efficiently propagates object masks from previous frames to the current frame using two feature scales of 16 and 8. As a testament to the effectiveness of our design, we achieved the 1st place in the EPIC-KITCHENS TREK-150 Object Tracking Challenge.
Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods. One potential reason is its label assignment strategy during training that consistently binds the tracked objects with tracking queries and then assigns the few newborns to detection queries. With one-to-one bipartite matching, such an assignment will yield unbalanced training, i.e., scarce positive samples for detection queries, especially for an enclosed scene, as the majority of the newborns come on stage at the beginning of videos. Thus, e2e-MOT will be easier to yield a tracking terminal without renewal or re-initialization, compared to other tracking-by-detection methods. To alleviate this problem, we present Co-MOT, a simple and effective method to facilitate e2e-MOT by a novel coopetition label assignment with a shadow concept. Specifically, we add tracked objects to the matching targets for detection queries when performing the label assignment for training the intermediate decoders. For query initialization, we expand each query by a set of shadow counterparts with limited disturbance to itself. With extensive ablations, Co-MOT achieves superior performance without extra costs, e.g., 69.4% HOTA on DanceTrack and 52.8% TETA on BDD100K. Impressively, Co-MOT only requires 38\% FLOPs of MOTRv2 to attain a similar performance, resulting in the 1.4$\times$ faster inference speed.