Sijia Chen

Sijia Chen, Yanqiu Yu, En Yu et al.

Referring Multi-Object Tracking (RMOT) aims to track targets specified by language instructions. However, existing RMOT paradigms heavily rely on explicit visual-textual matching and consequently fail to generalize to complex instructions that require logical reasoning. To overcome this, we propose Reasoning-based Multi-Object Tracking (ReaMOT), a novel task that elevates tracking to a cognitive level, requiring models to infer and track specific targets satisfying implicit constraints via logical reasoning. To advance this field, we construct the ReaMOT Challenge, a comprehensive benchmark featuring a tailored metric suite and a large scale dataset. This dataset comprises 1,156 language instructions, 423,359 image language pairs, and 869 distinct video sequences systematically categorized into six distinct evaluation scenarios, with over 75\% of the instructions dedicated to High Level Reasoning. Furthermore, recognizing that traditional trackers lack cognitive capacity while direct application of Large Vision-Language Model (LVLM) yields severe temporal inconsistencies, we propose ReaTrack. Driven by the insight to decouple high-level cognitive localization from low-level physical motion continuity, this training-free framework dynamically aligns the semantic detections of a Thinking-variant LVLM with the robust motion priors of SAM2. Extensive experiments on the ReaMOT Challenge benchmark demonstrate that ReaTrack establishes a new leading performance standard. Notably, it achieves a more than threefold improvement in RHOTA on the High Level Reasoning subset. Our dataset and code will be available at https://github.com/chen-si-jia/ReaMOT.

Sijia Chen, Baochun Li

Visual grounding (VG) tasks involve explicit cross-modal alignment, as semantically corresponding image regions are to be located for the language phrases provided. Existing approaches complete such visual-text reasoning in a single-step manner. Their performance causes high demands on large-scale anchors and over-designed multi-modal fusion modules based on human priors, leading to complicated frameworks that may be difficult to train and overfit to specific scenarios. Even worse, such once-for-all reasoning mechanisms are incapable of refining boxes continuously to enhance query-region matching. In contrast, in this paper, we formulate an iterative reasoning process by denoising diffusion modeling. Specifically, we propose a language-guided diffusion framework for visual grounding, LG-DVG, which trains the model to progressively reason queried object boxes by denoising a set of noisy boxes with the language guide. To achieve this, LG-DVG gradually perturbs query-aligned ground truth boxes to noisy ones and reverses this process step by step, conditional on query semantics. Extensive experiments for our proposed framework on five widely used datasets validate the superior performance of solving visual grounding, a cross-modal alignment task, in a generative way. The source codes are available at https://github.com/iQua/vgbase/tree/main/examples/DiffusionVG.

Sijia Chen, En Yu, Jinyang Li et al.

Multiple Object Tracking (MOT) is a critical area within computer vision, with a broad spectrum of practical implementations. Current research has primarily focused on the development of tracking algorithms and enhancement of post-processing techniques. Yet, there has been a lack of thorough examination concerning the nature of tracking data it self. In this study, we pioneer an exploration into the distribution patterns of tracking data and identify a pronounced long-tail distribution issue within existing MOT datasets. We note a significant imbalance in the distribution of trajectory lengths across different pedestrians, a phenomenon we refer to as ``pedestrians trajectory long-tail distribution''. Addressing this challenge, we introduce a bespoke strategy designed to mitigate the effects of this skewed distribution. Specifically, we propose two data augmentation strategies, including Stationary Camera View Data Augmentation (SVA) and Dynamic Camera View Data Augmentation (DVA) , designed for viewpoint states and the Group Softmax (GS) module for Re-ID. SVA is to backtrack and predict the pedestrian trajectory of tail classes, and DVA is to use diffusion model to change the background of the scene. GS divides the pedestrians into unrelated groups and performs softmax operation on each group individually. Our proposed strategies can be integrated into numerous existing tracking systems, and extensive experimentation validates the efficacy of our method in reducing the influence of long-tail distribution on multi-object tracking performance. The code is available at https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT.

Shiyin Lu, Yang Li, Yu Xia et al.

We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an optional "thinking mode" at inference time, allowing users to trade latency for enhanced accuracy on difficult inputs. The model is trained via a comprehensive five-phase curriculum that progressively builds its skills. The process begins with foundational visual and multimodal pretraining, advances through large-scale instruction tuning, and culminates in alignment and reasoning enhancement using DPO and GRPO. To scale these upgrades efficiently, we employ multimodal data packing and hybrid parallelism, yielding a significant end-to-end speedup. We release two open-source models: Ovis2.5-9B and Ovis2.5-2B. The latter continues the "small model, big performance" philosophy of Ovis2, making it ideal for resource-constrained, on-device scenarios. On the OpenCompass multimodal leaderboard, Ovis2.5-9B averages 78.3, marking a substantial improvement over its predecessor, Ovis2-8B, and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9, establishing SOTA for its size. Beyond aggregate scores, Ovis2.5 achieves leading results on STEM benchmarks, exhibits strong capabilities on grounding and video tasks, and achieves open-source SOTA at its scale for complex chart analysis.

Sijia Chen, En Yu, Wenbing Tao

Referring Multi-Object Tracking (RMOT) is an important topic in the current tracking field. Its task form is to guide the tracker to track objects that match the language description. Current research mainly focuses on referring multi-object tracking under single-view, which refers to a view sequence or multiple unrelated view sequences. However, in the single-view, some appearances of objects are easily invisible, resulting in incorrect matching of objects with the language description. In this work, we propose a new task, called Cross-view Referring Multi-Object Tracking (CRMOT). It introduces the cross-view to obtain the appearances of objects from multiple views, avoiding the problem of the invisible appearances of objects in RMOT task. CRMOT is a more challenging task of accurately tracking the objects that match the language description and maintaining the identity consistency of objects in each cross-view. To advance CRMOT task, we construct a cross-view referring multi-object tracking benchmark based on CAMPUS and DIVOTrack datasets, named CRTrack. Specifically, it provides 13 different scenes and 221 language descriptions. Furthermore, we propose an end-to-end cross-view referring multi-object tracking method, named CRTracker. Extensive experiments on the CRTrack benchmark verify the effectiveness of our method. The dataset and code are available at https://github.com/chen-si-jia/CRMOT.

Sijia Chen, Baochun Li, Di Niu

The reasoning performance of Large Language Models (LLMs) on a wide range of problems critically relies on chain-of-thought prompting, which involves providing a few chain of thought demonstrations as exemplars in prompts. Recent work, e.g., Tree of Thoughts, has pointed out the importance of exploration and self-evaluation in reasoning step selection for complex problem solving. In this paper, we present Boosting of Thoughts (BoT), an automated prompting framework for problem solving with LLMs by iteratively exploring and self-evaluating many trees of thoughts in order to acquire an ensemble of trial-and-error reasoning experiences, which will serve as a new form of prompting to solve the complex problem. Starting from a simple prompt without requiring examples, BoT iteratively explores and evaluates a large collection of reasoning steps, and more importantly, uses error analysis obtained from the LLM on them to explicitly revise prompting, which in turn enhances reasoning step generation, until a final answer is attained. Our experiments with GPT-4 and Llama2 across extensive complex mathematical problems demonstrate that BoT consistently achieves higher or comparable problem-solving rates than other advanced prompting approaches.

Sijia Chen, Baochun Li

Large language models (LLMs) have been routinely used to solve various tasks using step-by-step reasoning. However, the structure of intermediate reasoning steps, or thoughts, is rigid and unidirectional, such as chains, trees, or acyclic-directed graphs. Consequently, the resulting inflexible and forward-only reasoning may not address challenging tasks and fail when the LLM frequently gives false responses, i.e., ``hallucinations''. This paper proposes a new reasoning framework, called Thought Rollback (TR), allowing LLMs to adaptively build thought structure while maintaining effective reasoning toward problem-solving under ``hallucinations''. The core mechanism of TR is rolling back thoughts, which allows LLMs to perform error analysis on thoughts, and thus roll back to any previously mistaken thought for revision. Subsequently, by including such trial-and-error in the prompt to guide the LLM, each rollback leads to one more reliable reasoning path. Therefore, starting with a simple prompt without human annotations, LLM with TR adaptively and gradually explores thoughts for a correct solution. Comprehensive experiments on mathematical problems and multi-task reasoning demonstrate the state-of-the-art performance of TR in terms of problem-solving rate and interaction cost. For instance, the solving rate of GPT-4 with TR outperforms the current best by $9\%$ on the MATH dataset.

Yiming Li, Shan Liu, Yu Chen et al.

As the successor of H.265/HEVC, the new versatile video coding standard (H.266/VVC) can provide up to 50% bitrate saving with the same subjective quality, at the cost of increased decoding complexity. To accelerate the application of the new coding standard, a real-time H.266/VVC software decoder that can support various platforms is implemented, where SIMD technologies, parallelism optimization, and the acceleration strategies based on the characteristics of each coding tool are applied. As the mobile devices have become an essential carrier for video services nowadays, the mentioned optimization efforts are not only implemented for the x86 platform, but more importantly utilized to highly optimize the decoding performance on the ARM platform in this work. The experimental results show that when running on the Apple A14 SoC (iPhone 12pro), the average single-thread decoding speed of the present implementation can achieve 53fps (RA and LB) for full HD (1080p) bitstreams generated by VTM-11.0 reference software using 8bit Common Test Conditions (CTC). When multi-threading is enabled, an average of 32 fps (RA) can be achieved when decoding the 4K bitstreams.

Sijia Chen, Yu Wang, Li Huang et al.

A practical autonomous driving system urges the need to reliably and accurately detect vehicles and persons. In this report, we introduce a state-of-the-art 2D object detection system for autonomous driving scenarios. Specifically, we integrate both popular two-stage detector and one-stage detector with anchor free fashion to yield a robust detection. Furthermore, we train multiple expert models and design a greedy version of the auto ensemble scheme that automatically merges detections from different models. Notably, our overall detection system achieves 70.28 L2 mAP on the Waymo Open Dataset v1.2, ranking the 2nd place in the 2D detection track of the Waymo Open Dataset Challenges.

Yu Wang, Sijia Chen, Li Huang et al.

This technical report presents the online and real-time 2D and 3D multi-object tracking (MOT) algorithms that reached the 1st places on both Waymo Open Dataset 2D tracking and 3D tracking challenges. An efficient and pragmatic online tracking-by-detection framework named HorizonMOT is proposed for camera-based 2D tracking in the image space and LiDAR-based 3D tracking in the 3D world space. Within the tracking-by-detection paradigm, our trackers leverage our high-performing detectors used in the 2D/3D detection challenges and achieved 45.13% 2D MOTA/L2 and 63.45% 3D MOTA/L2 in the 2D/3D tracking challenges.

Zhuangzhuang Ding, Yihan Hu, Runzhou Ge et al.

In this technical report, we introduce our winning solution "HorizonLiDAR3D" for the 3D detection track and the domain adaptation track in Waymo Open Dataset Challenge at CVPR 2020. Many existing 3D object detectors include prior-based anchor box design to account for different scales and aspect ratios and classes of objects, which limits its capability of generalization to a different dataset or domain and requires post-processing (e.g. Non-Maximum Suppression (NMS)). We proposed a one-stage, anchor-free and NMS-free 3D point cloud object detector AFDet, using object key-points to encode the 3D attributes, and to learn an end-to-end point cloud object detection without the need of hand-engineering or learning the anchors. AFDet serves as a strong baseline in our winning solution and significant improvements are made over this baseline during the challenges. Specifically, we design stronger networks and enhance the point cloud data using densification and point painting. To leverage camera information, we append/paint additional attributes to each point by projecting them to camera space and gathering image-based perception information. The final detection performance also benefits from model ensemble and Test-Time Augmentation (TTA) in both the 3D detection track and the domain adaptation track. Our solution achieves the 1st place with 77.11% mAPH/L2 and 69.49% mAPH/L2 respectively on the 3D detection track and the domain adaptation track.

Runzhou Ge, Zhuangzhuang Ding, Yihan Hu et al.

High-efficiency point cloud 3D object detection operated on embedded systems is important for many robotics applications including autonomous driving. Most previous works try to solve it using anchor-based detection methods which come with two drawbacks: post-processing is relatively complex and computationally expensive; tuning anchor parameters is tricky. We are the first to address these drawbacks with an anchor free and Non-Maximum Suppression free one stage detector called AFDet. The entire AFDet can be processed efficiently on a CNN accelerator or a GPU with the simplified post-processing. Without bells and whistles, our proposed AFDet performs competitively with other one stage anchor-based methods on KITTI validation set and Waymo Open Dataset validation set.

Sijia Chen, Bin Song, Xiaojiang Du et al.

Deep Models, typically Deep neural networks, have millions of parameters, analyze medical data accurately, yet in a time-consuming method. However, energy cost effectiveness and computational efficiency are important for prerequisites developing and deploying mobile-enabled devices, the mainstream trend in connected healthcare.

Sijia Chen, Bin Song, Jie Guo et al.

The Localization of the target object for data retrieval is a key issue in the Intelligent and Connected Transportation Systems (ICTS). However, due to lack of intelligence in the traditional transportation system, it can take tremendous resources to manually retrieve and locate the queried objects among a large number of images. In order to solve this issue, we propose an effective method to query-based object localization that uses artificial intelligence techniques to automatically locate the queried object in the complex background. The presented method is termed as Fine-grained and Progressive Attention Localization Network (FPAN), which uses an image and a queried object as input to accurately locate the target object in the image. Specifically, the fine-grained attention module is naturally embedded into each layer of the convolution neural network (CNN), thereby gradually suppressing the regions that are irrelevant to the queried object and eventually shrinking attention to the target area. We further employ top-down attentions fusion algorithm operated by a learnable cascade up-sampling structure to establish the connection between the attention map and the exact location of the queried object in the original image. Furthermore, the FPAN is trained by multi-task learning with box segmentation loss and cosine loss. At last, we conduct comprehensive experiments on both queried-based digit localization and object tracking with synthetic and benchmark datasets, respectively. The experimental results show that our algorithm is far superior to other algorithms in the synthesis datasets and outperforms most existing trackers on the OTB and VOT datasets.