In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data in safety-critical perception tasks. INTACT combines meta-learning with adversarial curriculum training (ACT) to systematically address challenges posed by data corruption and sparsity in 3D point clouds. The meta-learning phase equips a teacher network with task-agnostic priors, enabling it to generate robust saliency maps that identify critical data regions. The ACT phase leverages these saliency maps to progressively expose a student network to increasingly complex noise patterns, ensuring targeted perturbation and improved noise resilience. INTACT's effectiveness is demonstrated through comprehensive evaluations on object detection, tracking, and classification benchmarks using diverse datasets, including KITTI, Argoverse, and ModelNet40. Results indicate that INTACT improves model robustness by up to 20% across all tasks, outperforming standard adversarial and curriculum training methods. This framework not only addresses the limitations of conventional training strategies but also offers a scalable and efficient solution for real-world deployment in resource-constrained safety-critical systems. INTACT's principled integration of meta-learning and adversarial training establishes a new paradigm for noise-tolerant 3D perception in safety-critical applications. INTACT improved KITTI Multiple Object Tracking Accuracy (MOTA) by 9.6% (64.1% -> 75.1%) and by 12.4% under Gaussian noise (52.5% -> 73.7%). Similarly, KITTI mean Average Precision (mAP) rose from 59.8% to 69.8% (50% point drop) and 49.3% to 70.9% (Gaussian noise), highlighting the framework's ability to enhance deep learning model resilience in safety-critical object tracking scenarios.
Next-frame prediction in videos is crucial for applications such as autonomous driving, object tracking, and motion prediction. The primary challenge in next-frame prediction lies in effectively capturing and processing both spatial and temporal information from previous video sequences. The transformer architecture, known for its prowess in handling sequence data, has made remarkable progress in this domain. However, transformer-based next-frame prediction models face notable issues: (a) The multi-head self-attention (MHSA) mechanism requires the input embedding to be split into $N$ chunks, where $N$ is the number of heads. Each segment captures only a fraction of the original embeddings information, which distorts the representation of the embedding in the latent space, resulting in a semantic dilution problem; (b) These models predict the embeddings of the next frames rather than the frames themselves, but the loss function based on the errors of the reconstructed frames, not the predicted embeddings -- this creates a discrepancy between the training objective and the model output. We propose a Semantic Concentration Multi-Head Self-Attention (SCMHSA) architecture, which effectively mitigates semantic dilution in transformer-based next-frame prediction. Additionally, we introduce a loss function that optimizes SCMHSA in the latent space, aligning the training objective more closely with the model output. Our method demonstrates superior performance compared to the original transformer-based predictors.
The analysis of extended video content poses unique challenges in artificial intelligence, particularly when dealing with the complexity of tracking and understanding visual elements across time. Current methodologies that process video frames sequentially struggle to maintain coherent tracking of objects, especially when these objects temporarily vanish and later reappear in the footage. A critical limitation of these approaches is their inability to effectively identify crucial moments in the video, largely due to their limited grasp of temporal relationships. To overcome these obstacles, we present GraphVideoAgent, a cutting-edge system that leverages the power of graph-based object tracking in conjunction with large language model capabilities. At its core, our framework employs a dynamic graph structure that maps and monitors the evolving relationships between visual entities throughout the video sequence. This innovative approach enables more nuanced understanding of how objects interact and transform over time, facilitating improved frame selection through comprehensive contextual awareness. Our approach demonstrates remarkable effectiveness when tested against industry benchmarks. In evaluations on the EgoSchema dataset, GraphVideoAgent achieved a 2.2 improvement over existing methods while requiring analysis of only 8.2 frames on average. Similarly, testing on the NExT-QA benchmark yielded a 2.0 performance increase with an average frame requirement of 8.1. These results underscore the efficiency of our graph-guided methodology in enhancing both accuracy and computational performance in long-form video understanding tasks.
Inspection systems utilizing unmanned aerial vehicles (UAVs) equipped with thermal cameras are increasingly popular for the maintenance of photovoltaic (PV) power plants. However, automation of the inspection task is a challenging problem as it requires precise navigation to capture images from optimal distances and viewing angles. This paper presents a novel localization pipeline that directly integrates PV module detection with UAV navigation, allowing precise positioning during inspection. Detections are used to identify the power plant structures in the image and associate these with the power plant model. We define visually recognizable anchor points for the initial association and use object tracking to discern global associations. We present three distinct methods for visual segmentation of PV modules based on traditional computer vision, deep learning, and their fusion, and we evaluate their performance in relation to the proposed localization pipeline. The presented methods were verified and evaluated using custom aerial inspection data sets, demonstrating their robustness and applicability for real-time navigation. Additionally, we evaluate the influence of the power plant model's precision on the localization methods.
Object Tracking is essential for many computer vision applications, such as autonomous navigation, surveillance, and robotics. Unlike Passive Object Tracking (POT), which relies on static camera viewpoints to detect and track objects across consecutive frames, Active Object Tracking (AOT) requires a controller agent to actively adjust its viewpoint to maintain visual contact with a moving target in complex environments. Existing AOT solutions are predominantly single-agent-based, which struggle in dynamic and complex scenarios due to limited information gathering and processing capabilities, often resulting in suboptimal decision-making. Alleviating these limitations necessitates the development of a multi-agent system where different agents perform distinct roles and collaborate to enhance learning and robustness in dynamic and complex environments. Although some multi-agent approaches exist for AOT, they typically rely on external auxiliary agents, which require additional devices, making them costly. In contrast, we introduce the Collaborative System for Active Object Tracking (CSAOT), a method that leverages multi-agent deep reinforcement learning (MADRL) and a Mixture of Experts (MoE) framework to enable multiple agents to operate on a single device, thereby improving tracking performance and reducing costs. Our approach enhances robustness against occlusions and rapid motion while optimizing camera movements to extend tracking duration. We validated the effectiveness of CSAOT on various interactive maps with dynamic and stationary obstacles.
We introduce YOLO11-JDE, a fast and accurate multi-object tracking (MOT) solution that combines real-time object detection with self-supervised Re-Identification (Re-ID). By incorporating a dedicated Re-ID branch into YOLO11s, our model performs Joint Detection and Embedding (JDE), generating appearance features for each detection. The Re-ID branch is trained in a fully self-supervised setting while simultaneously training for detection, eliminating the need for costly identity-labeled datasets. The triplet loss, with hard positive and semi-hard negative mining strategies, is used for learning discriminative embeddings. Data association is enhanced with a custom tracking implementation that successfully integrates motion, appearance, and location cues. YOLO11-JDE achieves competitive results on MOT17 and MOT20 benchmarks, surpassing existing JDE methods in terms of FPS and using up to ten times fewer parameters. Thus, making our method a highly attractive solution for real-world applications.
Multi-object tracking (MOT) is a rising topic in video processing technologies and has important application value in consumer electronics. Currently, tracking-by-detection (TBD) is the dominant paradigm for MOT, which performs target detection and association frame by frame. However, the association performance of TBD methods degrades in complex scenes with heavy occlusions, which hinders the application of such methods in real-world scenarios.To this end, we incorporate pseudo-depth cues to enhance the association performance and propose Pseudo-Depth SORT (PD-SORT). First, we extend the Kalman filter state vector with pseudo-depth states. Second, we introduce a novel depth volume IoU (DVIoU) by combining the conventional 2D IoU with pseudo-depth. Furthermore, we develop a quantized pseudo-depth measurement (QPDM) strategy for more robust data association. Besides, we also integrate camera motion compensation (CMC) to handle dynamic camera situations. With the above designs, PD-SORT significantly alleviates the occlusion-induced ambiguous associations and achieves leading performances on DanceTrack, MOT17, and MOT20. Note that the improvement is especially obvious on DanceTrack, where objects show complex motions, similar appearances, and frequent occlusions. The code is available at https://github.com/Wangyc2000/PD_SORT.
This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the original MLLMs' ability to perceive fine-grained details and capture long-form temporal structure in videos. Specifically, our approach incorporates dense vision task annotations into MLLMs using direct preference optimization and develops compact spatiotemporal representations through adaptive hierarchical token compression. Experimental results demonstrate this unique design of LRC greatly improves the results of video MLLM in mainstream video understanding benchmarks (short & long), enabling the MLLM to memorize significantly longer video inputs (at least 6x longer than the original), and master specialized vision capabilities like object tracking and segmentation. Our work highlights the importance of multimodal context richness (length and fineness) in empowering MLLM's innate abilites (focus and memory), providing new insights for future research on video MLLM. Code and models are available at https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2.5
In the realm of multi-object tracking, the challenge of accurately capturing the spatial and temporal relationships between objects in video sequences remains a significant hurdle. This is further complicated by frequent occurrences of mutual occlusions among objects, which can lead to tracking errors and reduced performance in existing methods. Motivated by these challenges, we propose a novel adaptive key frame mining strategy that addresses the limitations of current tracking approaches. Specifically, we introduce a Key Frame Extraction (KFE) module that leverages reinforcement learning to adaptively segment videos, thereby guiding the tracker to exploit the intrinsic logic of the video content. This approach allows us to capture structured spatial relationships between different objects as well as the temporal relationships of objects across frames. To tackle the issue of object occlusions, we have developed an Intra-Frame Feature Fusion (IFF) module. Unlike traditional graph-based methods that primarily focus on inter-frame feature fusion, our IFF module uses a Graph Convolutional Network (GCN) to facilitate information exchange between the target and surrounding objects within a frame. This innovation significantly enhances target distinguishability and mitigates tracking loss and appearance similarity due to occlusions. By combining the strengths of both long and short trajectories and considering the spatial relationships between objects, our proposed tracker achieves impressive results on the MOT17 dataset, i.e., 68.6 HOTA, 81.0 IDF1, 66.6 AssA, and 893 IDS, proving its effectiveness and accuracy.
Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and hierarchical dependencies, while image scores fail to assess temporal consistency. We present SST-EM (Semantic, Spatial, and Temporal Evaluation Metric), a novel evaluation framework that leverages modern Vision-Language Models (VLMs), Object Detection, and Temporal Consistency checks. SST-EM comprises four components: (1) semantic extraction from frames using a VLM, (2) primary object tracking with Object Detection, (3) focused object refinement via an LLM agent, and (4) temporal consistency assessment using a Vision Transformer (ViT). These components are integrated into a unified metric with weights derived from human evaluations and regression analysis. The name SST-EM reflects its focus on Semantic, Spatial, and Temporal aspects of video evaluation. SST-EM provides a comprehensive evaluation of semantic fidelity and temporal smoothness in video editing. The source code is available in the \textbf{\href{https://github.com/custommetrics-sst/SST_CustomEvaluationMetrics.git}{GitHub Repository}}.
Timber represents an increasingly valuable and versatile resource. However, forestry operations such as harvesting, handling and measuring logs still require substantial human labor in remote environments posing significant safety risks. Progressively automating these tasks has the potential of increasing their efficiency as well as safety, but requires an accurate detection of individual logs as well as live trees and their context. Although initial approaches have been proposed for this challenging application domain, specialized data and algorithms are still too scarce to develop robust solutions. To mitigate this gap, we introduce the TimberVision dataset, consisting of more than 2k annotated RGB images containing a total of 51k trunk components including cut and lateral surfaces, thereby surpassing any existing dataset in this domain in terms of both quantity and detail by a large margin. Based on this data, we conduct a series of ablation experiments for oriented object detection and instance segmentation and evaluate the influence of multiple scene parameters on model performance. We introduce a generic framework to fuse the components detected by our models for both tasks into unified trunk representations. Furthermore, we automatically derive geometric properties and apply multi-object tracking to further enhance robustness. Our detection and tracking approach provides highly descriptive and accurate trunk representations solely from RGB image data, even under challenging environmental conditions. Our solution is suitable for a wide range of application scenarios and can be readily combined with other sensor modalities.
3D single object tracking (3DSOT) in LiDAR point clouds is a critical task for outdoor perception, enabling real-time perception of object location, orientation, and motion. Despite the impressive performance of current 3DSOT methods, evaluating them on clean datasets inadequately reflects their comprehensive performance, as the adverse weather conditions in real-world surroundings has not been considered. One of the main obstacles is the lack of adverse weather benchmarks for the evaluation of 3DSOT. To this end, this work proposes a challenging benchmark for LiDAR-based 3DSOT in adverse weather, which comprises two synthetic datasets (KITTI-A and nuScenes-A) and one real-world dataset (CADC-SOT) spanning three weather types: rain, fog, and snow. Based on this benchmark, five representative 3D trackers from different tracking frameworks conducted robustness evaluation, resulting in significant performance degradations. This prompts the question: What are the factors that cause current advanced methods to fail on such adverse weather samples? Consequently, we explore the impacts of adverse weather and answer the above question from three perspectives: 1) target distance; 2) template shape corruption; and 3) target shape corruption. Finally, based on domain randomization and contrastive learning, we designed a dual-branch tracking framework for adverse weather, named DRCT, achieving excellent performance in benchmarks.
We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to autoregressively predict future tokens. Our models are pre-trained on a diverse dataset of videos and images comprising over 1 trillion visual tokens. We explore different architectural, training, and inference design choices. We evaluate the learned visual representations on a range of downstream tasks including image recognition, video classification, object tracking, and robotics. Our results demonstrate that, despite minimal inductive biases, autoregressive pre-training leads to competitive performance across all benchmarks. Finally, we find that scaling our video models results in similar scaling curves to those seen in language models, albeit with a different rate. More details at https://brjathu.github.io/toto/
Long-form video understanding with Large Vision Language Models is challenged by the need to analyze temporally dispersed yet spatially concentrated key moments within limited context windows. In this work, we introduce VideoMindPalace, a new framework inspired by the "Mind Palace", which organizes critical video moments into a topologically structured semantic graph. VideoMindPalace organizes key information through (i) hand-object tracking and interaction, (ii) clustered activity zones representing specific areas of recurring activities, and (iii) environment layout mapping, allowing natural language parsing by LLMs to provide grounded insights on spatio-temporal and 3D context. In addition, we propose the Video MindPalace Benchmark (VMB), to assess human-like reasoning, including spatial localization, temporal reasoning, and layout-aware sequential understanding. Evaluated on VMB and established video QA datasets, including EgoSchema, NExT-QA, IntentQA, and the Active Memories Benchmark, VideoMindPalace demonstrates notable gains in spatio-temporal coherence and human-aligned reasoning, advancing long-form video analysis capabilities in VLMs.
Tracking and acquiring simultaneous optical images of randomly moving targets obscured by scattering media remains a challenging problem of importance to many applications that require precise object localization and identification. In this work we develop an end-to-end neuromorphic optical engineering and computational approach to demonstrate how to track and image normally invisible objects by combining an event detecting camera with a multistage neuromorphic deep learning strategy. Photons emerging from dense scattering media are detected by the event camera and converted to pixel-wise asynchronized spike trains - a first step in isolating object-specific information from the dominant uninformative background. Spiking data is fed into a deep spiking neural network (SNN) engine where object tracking and image reconstruction are performed by two separate yet interconnected modules running in parallel in discrete time steps over the event duration. Through benchtop experiments we demonstrate tracking and imaging randomly moving objects in dense turbid media as well as image reconstruction of spatially stationary but optically dynamic objects. Standardized character sets serve as representative proxies for geometrically complex objects, underscoring the method's generality. The results highlight the advantages of a fully neuromorphic approach in meeting a major imaging technology with high computational efficiency and low power consumption.
Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets.
Changes in room acoustics, such as modifications to surface absorption or the insertion of a scattering object, significantly impact measured room impulse responses (RIRs). These changes can affect the performance of systems used in echo cancellation and active acoustics and support tasks such as navigation and object tracking. Recognizing and quantifying such changes is, therefore, critical for advancing technologies based on room acoustics. This study introduces a method for analyzing acoustic environment changes by evaluating the similarity of consecutively recorded RIRs. Short-time coherence is employed to characterize modifications, including changes in wall absorption or the presence of a moving person in the room. A sensitivity rating is further used to quantify the magnitude of these changes. The results clearly differentiate between types of modifications -- atmospheric variation, changes in absorption, and human presence. The methods described provide a novel approach to analyzing and interpreting room acoustics, emphasizing RIR similarity and extracting information from temporal and spectral signal properties.
The evolution of Advanced Driver Assistance Systems (ADAS) has increased the need for robust and generalizable algorithms for multi-object tracking. Traditional statistical model-based tracking methods rely on predefined motion models and assumptions about system noise distributions. Although computationally efficient, they often lack adaptability to varying traffic scenarios and require extensive manual design and parameter tuning. To address these issues, we propose a novel 3D multi-object tracking approach for vehicles, HybridTrack, which integrates a data-driven Kalman Filter (KF) within a tracking-by-detection paradigm. In particular, it learns the transition residual and Kalman gain directly from data, which eliminates the need for manual motion and stochastic parameter modeling. Validated on the real-world KITTI dataset, HybridTrack achieves 82.72% HOTA accuracy, significantly outperforming state-of-the-art methods. We also evaluate our method under different configurations, achieving the fastest processing speed of 112 FPS. Consequently, HybridTrack eliminates the dependency on scene-specific designs while improving performance and maintaining real-time efficiency. The code is publicly available at: https://github.com/leandro-svg/HybridTrack.
Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context methods fail to consider the importance of each patch within a reference frame, making them susceptible to noise and redundant tokens, which deteriorates tracking performance. To address this challenge, we propose a new token context-aware tracking pipeline named LMTrack, designed to automatically learn high-quality reference tokens for efficient visual tracking. Embracing the principle of Less is More, the core idea of LMTrack is to analyze the importance distribution of all reference tokens, where important tokens are collected, continually attended to, and updated. Specifically, a novel Token Context Memory module is designed to dynamically collect high-quality spatio-temporal information of a target in an autoregressive manner, eliminating redundant background tokens from the reference frames. Furthermore, an effective Unidirectional Token Attention mechanism is designed to establish dependencies between reference tokens and search frame, enabling robust cross-frame association and target localization. Extensive experiments demonstrate the superiority of our tracker, achieving state-of-the-art results on tracking benchmarks such as GOT-10K, TrackingNet, and LaSOT.
In this paper, we propose a simple yet unified single object tracking (SOT) framework, dubbed SUTrack. It consolidates five SOT tasks (RGB-based, RGB-Depth, RGB-Thermal, RGB-Event, RGB-Language Tracking) into a unified model trained in a single session. Due to the distinct nature of the data, current methods typically design individual architectures and train separate models for each task. This fragmentation results in redundant training processes, repetitive technological innovations, and limited cross-modal knowledge sharing. In contrast, SUTrack demonstrates that a single model with a unified input representation can effectively handle various common SOT tasks, eliminating the need for task-specific designs and separate training sessions. Additionally, we introduce a task-recognition auxiliary training strategy and a soft token type embedding to further enhance SUTrack's performance with minimal overhead. Experiments show that SUTrack outperforms previous task-specific counterparts across 11 datasets spanning five SOT tasks. Moreover, we provide a range of models catering edge devices as well as high-performance GPUs, striking a good trade-off between speed and accuracy. We hope SUTrack could serve as a strong foundation for further compelling research into unified tracking models. Code and models are available at github.com/chenxin-dlut/SUTrack.