Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where zero rewards from consistently incorrect candidate answers provide no learning signal, particularly in challenging tasks. To address this,we propose Multi-Expert Mutual Learning GRPO (MEML-GRPO), an innovative framework that utilizes diverse expert prompts as system prompts to generate a broader range of responses, substantially increasing the likelihood of identifying correct solutions. Additionally, we introduce an inter-expert mutual learning mechanism that facilitates knowledge sharing and transfer among experts, further boosting the model’s performance through RLVR. Extensive experiments across multiple reasoning benchmarks show that MEML-GRPO delivers significant improvements, achieving an average performance gain of 4.89% with Qwen and 11.33% with Llama, effectively overcoming the core limitations of traditional RLVR methods.

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.

Video anomaly detection (VAD) has been widely studied for its important applications in multimedia community. Recently, many Weakly Supervised VAD (WS-VAD) methods have been proposed, which tend to treat VAD as a classification task through multiple instance learning and result in the need to collect sufficient anomaly classes and samples to be used for training a classifier. However, anomaly events tend to be open-set and rare in real-world applications, so we often have difficulty collecting all anomaly classes and enough sample anomalies, which is a difficult situation for WS-VAD to cope with. To this end, we consider to treat VAD as an out-of-distribution detection task rather than a classification task and propose a simple but effective semi-supervised baseline method. First, we leverage the powerful zero-shot capability of large visual language models to generate summary text descriptions for videos and extract visual features as intermediates for subsequent use. Next, we use a text encoder to extract language features and combine them with visual features to obtain robust multimodal features. Finally, we introduce an out-of-distribution detection method that learns the center of normality in multimodal space from normal and unlabeled samples, while deviating abnormal samples from the center to cope with the scarcity of abnormal samples. To implement our baseline method, we also provide a new semi-supervised dataset by reorganizing an existing benchmark, which is the first available dataset in the VAD community that provides trimmed videos consisting of complete abnormal events. Experiments demonstrate that our method performs more robustly when fewer anomaly classes and anomaly samples collected.

Multiple Object Tracking (MOT) is a fundamental task in computer vision. Existing methods utilize motion information or appearance information to perform object tracking. However, these algorithms still struggle with special circumstances, such as occlusion and blurring in complex scenes. Inspired by the fact that people can pinpoint objects through verbal descriptions, we explore performing long-term robust tracking using semantic features of objects. Motivated by the success of the multimodal foundation model in text-image alignment, we reconsider the appearance feature extraction module in MOT and propose a Foundation model Driven multi-object tracker (FDTracker). Specifically, we propose a two-stage trained appearance feature extractor. In the first stage, using a single image of the object as input, the model could capture the attributes of objects with the assistance of natural language instructions. In the second stage, using a sequence of images of objects as input, the model learns how to use these attributes to distinguish between different objects and connect the same object at different times. Finally, for coordinating appearance and motion information, we propose a reasonable combined strategy, which better facilitates trajectory assignment and reconnection. Extensive experiments on benchmarks demonstrate the robustness of FDTracker.

Person re-identification (Re-ID) is a crucial task in computer vision, aiming to recognize individuals across non-overlapping camera views. While recent advanced vision-language models (VLMs) excel in logical reasoning and multi-task generalization, their applications in Re-ID tasks remain limited. They either struggle to perform accurate matching based on identity-relevant features or assist image-dominated branches as auxiliary semantics. In this paper, we propose a novel framework ChatReID, that shifts the focus towards a text-side-dominated retrieval paradigm, enabling flexible and interactive re-identification. To integrate the reasoning abilities of language models into Re-ID pipelines, We first present a large-scale instruction dataset, which contains more than 8 million prompts to promote the model fine-tuning. Next. we introduce a hierarchical progressive tuning strategy, which endows Re-ID ability through three stages of tuning, i.e., from person attribute understanding to fine-grained image retrieval and to multi-modal task reasoning. Extensive experiments across ten popular benchmarks demonstrate that ChatReID outperforms existing methods, achieving state-of-the-art performance in all Re-ID tasks. More experiments demonstrate that ChatReID not only has the ability to recognize fine-grained details but also to integrate them into a coherent reasoning process.

The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image understanding, but there is still a lack of comparable datasets for videos. Additionally, many VideoLLMs are extensions of single-image VLMs, which may not efficiently handle the complexities of longer videos. In this study, we introduce a large-scale synthetic dataset created from proprietary models, using carefully designed prompts to tackle a wide range of questions. We also explore a dynamic visual token compression architecture that strikes a balance between computational efficiency and performance. Our proposed \model{} achieves state-of-the-art results across various video tasks and shows impressive generalization, setting new baselines in multi-image understanding. Notably, \model{} delivers an absolute improvement of 2.7\% over LLaVA-OneVision on VideoMME and 10.7\% on MuirBench. Codes are available at https://github.com/Hon-Wong/ByteVideoLLM

Computer-Aided Design (CAD) is pivotal in industrial manufacturing, with orthographic projection reasoning foundational to its entire workflow—encompassing design, manufacturing, and simulation. However, prevailing deep-learning approaches employ standard 3D reconstruction pipelines as an alternative, which often introduce imprecise dimensions and limit the parametric editability required for CAD workflows. Recently, some researchers adopt vision–language models (VLMs), particularly supervised fine-tuning (SFT), to tackle CAD-related challenges. SFT shows promise but often devolves into pattern memorization, resulting in poor out-of-distribution (OOD) performance on complex reasoning tasks. To tackle these limitations, we introduce CReFT-CAD, a two-stage fine-tuning paradigm: first, a curriculum-driven reinforcement learning stage with difficulty-aware rewards to steadily build reasoning abilities; second, supervised post-tuning to refine instruction following and semantic extraction. Complementing this, we release TriView2CAD, the first large-scale, open-source benchmark for orthographic projection reasoning, comprising 200,000 synthetic and 3,000 real-world orthographic projections with precise dimensional annotations and six interoperable data modalities. Benchmarking leading VLMs on orthographic projection reasoning, we show that CReFT-CAD significantly improves reasoning accuracy and OOD generalizability in real-world scenarios, providing valuable insights to advance CAD reasoning research. The code and adopted datasets are available at \url{https://github.com/KeNiu042/CReFT-CAD}.

Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among different layers, have been proposed to address classification tasks under varying computing resources. Existing approaches typically utilize the last classifier supported by the available resources for inference, as they believe that the last classifier always performs better across all classes. However, our findings indicate that earlier classifier heads can outperform the last head for certain classes. Based on this observation, we introduce the Collaborative Decision Making (CDM) module, which fuses the multiple classifier heads to enhance the inference performance of adaptive deep networks. CDM incorporates an uncertainty-aware fusion method based on evidential deep learning (EDL), that utilizes the reliability (uncertainty values) from the first c-1 classifiers to improve the c-th classifier' accuracy. We also design a balance term that reduces fusion saturation and unfairness issues caused by EDL constraints to improve the fusion quality of CDM. Finally, a regularized training strategy that uses the last classifier to guide the learning process of early classifiers is proposed to further enhance the CDM module's effect, called the Guided Collaborative Decision Making (GCDM) framework. The experimental evaluation demonstrates the effectiveness of our approaches. Results on ImageNet datasets show CDM and GCDM obtain 0.4% to 2.8% accuracy improvement (under varying computing resources) on popular adaptive networks. The code is available at the link https://github.com/Meteor-Stars/GCDM_AdaptiveNet.

Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR). Particularly, the characteristic of large categories poses challenges in dealing with zero-shot and few-shot Chinese characters. In this paper, inspired by the way humans recognize Chinese texts, we propose a two-stage framework for CTR. Firstly, we pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS). This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. Subsequently, the learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition through image-IDS matching. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on both Chinese character recognition (CCR) and CTR. The experimental results demonstrate that the proposed method performs best in CCR and outperforms previous methods in most scenarios of the CTR benchmark. It is worth noting that the proposed method can recognize zero-shot Chinese characters in text images without fine-tuning, whereas previous methods require fine-tuning when new classes appear. The code is available at https://github.com/FudanVI/FudanOCR/tree/main/image-ids-CTR.

In recent years, deep learning techniques have made significant advancements in text segmentation. However, most existing methods do not take into account that characters are composed of smaller components, such as strokes and other local patterns. Furthermore, the similarities between text components are crucial for effective text segmentation. With this in mind, we propose a multi-level Transformer-based method for text segmentation that incorporates a recognition module. To enhance the interaction between text components and extract features at different granularities, we introduce Global and Local Self-Attention blocks. Our recognition module is trained jointly with the segmentation module to improve the model’s ability to focus on text details and improve its perception of texts. By aggregating features from multiple granularities, our segmentation module produces accurate pixel-level mask predictions. The experimental results demonstrate the effectiveness of our approach on several text segmentation benchmarks and show that it outperforms existing methods.

Scene text recognition (STR) has attracted much attention due to its broad applications. The previous works pay more attention to dealing with the recognition of Latin text images with complex backgrounds by introducing language models or other auxiliary networks. Different from Latin texts, many vertical Chinese texts exist in natural scenes, which brings difficulties to current state-of-the-art STR methods. In this paper, we take the first attempt to extract orientation-independent visual features by disentangling content and orientation information of text images, thus recognizing both horizontal and vertical texts robustly in natural scenes. Specifically, we introduce a Character Image Reconstruction Network (CIRN) to recover corresponding printed character images with disentangled content and orientation information. We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information. To further validate the effectiveness of our method, we additionally collect a Vertical Chinese Text Recognition (VCTR) dataset. The experimental results show that the proposed method achieves 45.63\% improvement on VCTR when introducing CIRN to the baseline model.

Video text spotting (VTS) aims at extracting texts from videos, where text detection, tracking and recognition are conducted simultaneously. There have been some works that can tackle VTS; however, they may ignore the underlying semantic relationships among texts within a frame. We observe that the texts within a frame usually share similar semantics, which suggests that, if one text is predicted incorrectly by a text recognizer, it still has a chance to be corrected via semantic reasoning. In this paper, we propose an accurate video text spotter, VLSpotter, that reads texts visually, linguistically, and semantically. For ‘visually’, we propose a plug-and-play text-focused super-resolution module to alleviate motion blur and enhance video quality. For ‘linguistically’, a language model is employed to capture intra-text context to mitigate wrongly spelled text predictions. For ‘semantically’, we propose a text-wise semantic reasoning module to model inter-text semantic relationships and reason for better results. The experimental results on multiple VTS benchmarks demonstrate that the proposed VLSpotter outperforms the existing state-of-the-art methods in end-to-end video text spotting.

Multiple object tracking (MOT) tends to become more challenging when severe occlusions occur. In this paper, we analyze the limitations of traditional Convolutional Neural Network-based methods and Transformer-based methods in handling occlusions and propose DNMOT, an end-to-end trainable DeNoising Transformer for MOT. To address the challenge of occlusions, we explicitly simulate the scenarios when occlusions occur. Specifically, we augment the trajectory with noises during training and make our model learn the denoising process in an encoder-decoder architecture, so that our model can exhibit strong robustness and perform well under crowded scenes. Additionally, we propose a Cascaded Mask strategy to better coordinate the interaction between different types of queries in the decoder to prevent the mutual suppression between neighboring trajectories under crowded scenes. Notably, the proposed method requires no additional modules like matching strategy and motion state estimation in inference. We conduct extensive experiments on the MOT17, MOT20, and DanceTrack datasets, and the experimental results show that our method outperforms previous state-of-the-art methods by a clear margin.

Text segmentation is a crucial aspect of various text-related tasks, including text erasing, text editing, and font style transfer. In recent years, multiple text segmentation datasets, such as TextSeg focusing on Latin text segmentation and BTS on bilingual text segmentation, have been proposed. However, existing methods either disregard the annotations of text location or directly use pre-trained text detectors. In general, these methods cannot fully utilize the annotations of text location in the datasets. To explicitly incorporate text location information to guide text segmentation, we propose an end-to-end text-focused segmentation framework, where text detection and segmentation are jointly optimized. In the proposed framework, we first extract multi-level global visual features through residual convolution blocks and then predict the mask of text areas using a text detection head. Subsequently, we develop a text-focused module that compels the model to pay more attention to text areas. Specifically, we introduce two types of attention masks to extract corresponding features: text-aware and instance-aware features. Finally, we employ hierarchical Transformer encoders to fuse multi-level features and predict the text mask with a text segmentation head. To evaluate the effectiveness of our method, we conduct experiments on six text segmentation benchmarks. The experimental results demonstrate that the proposed method outperforms the previous state-of-the-art (SOTA) methods by a clear margin in most cases. The code and supplementary materials are available at https://github.com/FudanVI/FudanOCR/tree/main/text-focused-Transformers https://github.com/FudanVI/FudanOCR/tree/main/text-focused-Transformers.

Text segmentation is a challenging computer vision task with many downstream applications. Current text segmentation models need to be trained with pixel-level annotations, which requires a lot of labor cost. In this paper, we take the first attempt to perform weakly-supervised text instance segmentation through bridging text recognition and text segmentation. We observe that text recognition models are able to produce the attention localization of each text instance. Based on this observation, we propose a two-stage Text Adaptive Refinement (TAR) module to generate the pseudo labels based on the attention map of a text recognizer. Meanwhile, we develop a text segmentation module to take the rough attention location as input to predict segmentation masks, which are supervised by the aforementioned pseudo labels. In addition, we introduce a mask-augmented contrastive learning by treating the segmentation result as an augmented version of the input text image, thus improving the visual representation and further enhancing the performance of both recognition and segmentation. The experimental results demonstrate that the proposed method outperforms the state-of-the-art (SOTA) weakly-supervised generic segmentation methods by 18.95% and 17.80% in fgIoU on ICDAR13-FST and TextSeg. On MLT-S, COCO-TS and Total-Text, the proposed method achieves about 82% of the fully-supervised methods' performance. When evaluated on instance segmentation, the proposed method exceeds existing SOTA methods by 23.32% and 21.34% on ICDAR13-FST and TextSeg, respectively. Code and Supplementary Materials are available at https://github.com/FudanVI/FudanOCR/tree/main/weakly-text-segmentation.

In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains a challenge. Even though some super-resolution methods have been proposed to tackle this problem, they usually treat text images as general images while ignoring the fact that the visual quality of strokes (the atomic unit of text) plays an essential role for text recognition. According to Gestalt Psychology, humans are capable of composing parts of details into the most similar objects guided by prior knowledge. Likewise, when humans observe a low-resolution text image, they will inherently use partial stroke-level details to recover the appearance of holistic characters. Inspired by Gestalt Psychology, we put forward a Stroke-Aware Scene Text Image Super-Resolution method containing a Stroke-Focused Module (SFM) to concentrate on stroke-level internal structures of characters in text images. Specifically, we attempt to design rules for decomposing English characters and digits at stroke-level, then pre-train a text recognizer to provide stroke-level attention maps as positional clues with the purpose of controlling the consistency between the generated super-resolution image and high-resolution ground truth. The extensive experimental results validate that the proposed method can indeed generate more distinguishable images on TextZoom and manually constructed Chinese character dataset Degraded-IC13. Furthermore, since the proposed SFM is only used to provide stroke-level guidance when training, it will not bring any time overhead during the test phase. Code is available at https://github.com/FudanVI/FudanOCR/tree/main/text-gestalt.

Chinese character recognition (CCR) has drawn continuous research interest due to its wide applications. After decades of study, there still exist several challenges,e.g., different characters with similar appearance and the one-to-many problem. There is no unified solution to the above challenges as previous methods tend to address these problems separately. In this paper, we propose a Chinese character recognition method named Augmented Character Profile Matching (ACPM), which utilizes a collection of character knowledge from three decomposition levels to recognize Chinese characters. Specifically, the feature maps of each character image are utilized as the character-level knowledge. In addition, we introduce a radical-stroke counting module (RSC) to help produce augmented character profiles, including the number of radicals, the number of strokes, and the total length of strokes, which characterize the character more comprehensively. The feature maps of the character image and the outputs of the RSC module are collected to constitute a character profile for selecting the closest candidate character through joint matching. The experimental results show that the proposed method outperforms the state-of-the-art methods on both the ICDAR 2013 and CTW datasets by 0.35% and 2.23%, respectively. Moreover, it also clearly outperforms the compared methods in the zero-shot settings. Code is available at https://github.com/FudanVI/FudanOCR/tree/main/character-profile-matching.