Lei Yang

Haoran Sun, Renren Jin, Shaoyang Xu et al. · allen-ai, meta-ai

Large language models (LLMs) have demonstrated prowess in a wide range of tasks. However, many LLMs exhibit significant performance discrepancies between high- and low-resource languages. To mitigate this challenge, we present FuxiTranyu, an open-source multilingual LLM, which is designed to satisfy the need of the research community for balanced and high-performing multilingual capabilities. The base model, FuxiTranyu-8B, features 8 billion parameters and is trained from scratch on meticulously balanced multilingual data that contains 600 billion tokens covering 43 natural languages and 16 programming languages. We also develop two instruction-tuned models: FuxiTranyu-8B-SFT which is fine-tuned on a diverse multilingual instruction dataset, and FuxiTranyu-8B-DPO which is further refined with DPO on a preference dataset for enhanced alignment ability. Extensive experiments on a wide range of multilingual benchmarks demonstrate the competitive performance of FuxiTranyu against existing multilingual LLMs, e.g., BLOOM-7B, PolyLM-13B, and Mistral-7B-Instruct. Both neuron and representation interpretability analyses reveal that FuxiTranyu achieves consistent multilingual representations across languages. To promote further research into multilingual LLMs, we release both the base and instruction-tuned FuxiTranyu models together with 58 pre-training checkpoints at HuggingFace (see https://huggingface.co/TJUNLP/FuxiTranyu-8B) and Github (see https://github.com/tjunlp-lab/FuxiTranyu).

Wenqi Shao, Xun Zhao, Yixiao Ge et al. · tencent-ai

This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive. Recent advanced methods proposed several lightweight transferability metrics to predict the fine-tuning results. However, these approaches only capture static representations but neglect the fine-tuning dynamics. To this end, this paper proposes a new transferability metric, called \textbf{S}elf-challenging \textbf{F}isher \textbf{D}iscriminant \textbf{A}nalysis (\textbf{SFDA}), which has many appealing benefits that existing works do not have. First, SFDA can embed the static features into a Fisher space and refine them for better separability between classes. Second, SFDA uses a self-challenging mechanism to encourage different pre-trained models to differentiate on hard examples. Third, SFDA can easily select multiple pre-trained models for the model ensemble. Extensive experiments on $33$ pre-trained models of $11$ downstream tasks show that SFDA is efficient, effective, and robust when measuring the transferability of pre-trained models. For instance, compared with the state-of-the-art method NLEEP, SFDA demonstrates an average of $59.1$\% gain while bringing $22.5$x speedup in wall-clock time. The code will be available at \url{https://github.com/TencentARC/SFDA}.

Ailing Zeng, Xuan Ju, Lei Yang et al.

This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch. Unlike current solutions that estimate each frame in a video, DeciWatch introduces a simple yet effective sample-denoise-recover framework that only watches sparsely sampled frames, taking advantage of the continuity of human motions and the lightweight pose representation. Specifically, DeciWatch uniformly samples less than 10% video frames for detailed estimation, denoises the estimated 2D/3D poses with an efficient Transformer architecture, and then accurately recovers the rest of the frames using another Transformer-based network. Comprehensive experimental results on three video-based human pose estimation and body mesh recovery tasks with four datasets validate the efficiency and effectiveness of DeciWatch. Code is available at https://github.com/cure-lab/DeciWatch.

Lei Yang, Kaicheng Yu, Tao Tang et al.

While most recent autonomous driving system focuses on developing perception methods on ego-vehicle sensors, people tend to overlook an alternative approach to leverage intelligent roadside cameras to extend the perception ability beyond the visual range. We discover that the state-of-the-art vision-centric bird's eye view detection methods have inferior performances on roadside cameras. This is because these methods mainly focus on recovering the depth regarding the camera center, where the depth difference between the car and the ground quickly shrinks while the distance increases. In this paper, we propose a simple yet effective approach, dubbed BEVHeight, to address this issue. In essence, instead of predicting the pixel-wise depth, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods. On popular 3D detection benchmarks of roadside cameras, our method surpasses all previous vision-centric methods by a significant margin. The code is available at {\url{https://github.com/ADLab-AutoDrive/BEVHeight}}.

Sifeng He, Yue He, Minlong Lu et al.

Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for similarity matrix generation, and a temporal alignment module for copied segments localization. In contrast to previous methods demanding the handcrafted similarity matrix, TransVCL incorporates long-range temporal information between feature sequence pair using self- and cross- attention layers. With the joint design and optimization of three components, the similarity matrix can be learned to present more discriminative copied patterns, leading to significant improvements over previous methods on segment-level labeled datasets (VCSL and VCDB). Besides the state-of-the-art performance in fully supervised setting, the attention architecture facilitates TransVCL to further exploit unlabeled or simply video-level labeled data. Additional experiments of supplementing video-level labeled datasets including SVD and FIVR reveal the high flexibility of TransVCL from full supervision to semi-supervision (with or without video-level annotation). Code is publicly available at https://github.com/transvcl/TransVCL.

Lei Yang, Xinyu Zhang, Li Wang et al.

Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human annotations, we propose Mix-Teaching, an effective semi-supervised learning framework applicable to employ both labeled and unlabeled images in training stage. Mix-Teaching first generates pseudo-labels for unlabeled images by self-training. The student model is then trained on the mixed images possessing much more intensive and precise labeling by merging instance-level image patches into empty backgrounds or labeled images. This is the first to break the image-level limitation and put high-quality pseudo labels from multi frames into one image for semi-supervised training. Besides, as a result of the misalignment between confidence score and localization quality, it's hard to discriminate high-quality pseudo-labels from noisy predictions using only confidence-based criterion. To that end, we further introduce an uncertainty-based filter to help select reliable pseudo boxes for the above mixing operation. To the best of our knowledge, this is the first unified SSL framework for monocular 3D object detection. Mix-Teaching consistently improves MonoFlex and GUPNet by significant margins under various labeling ratios on KITTI dataset. For example, our method achieves around +6.34% AP@0.7 improvement against the GUPNet baseline on validation set when using only 10% labeled data. Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4.65% improvement on AP@0.7 for car detection, reaching 18.54% AP@0.7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard. The code and pretrained models will be released at https://github.com/yanglei18/Mix-Teaching.

Tong Wu, Jiarui Zhang, Xiao Fu et al.

Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases. To facilitate the development of 3D perception, reconstruction, and generation in the real world, we propose OmniObject3D, a large vocabulary 3D object dataset with massive high-quality real-scanned 3D objects. OmniObject3D has several appealing properties: 1) Large Vocabulary: It comprises 6,000 scanned objects in 190 daily categories, sharing common classes with popular 2D datasets (e.g., ImageNet and LVIS), benefiting the pursuit of generalizable 3D representations. 2) Rich Annotations: Each 3D object is captured with both 2D and 3D sensors, providing textured meshes, point clouds, multiview rendered images, and multiple real-captured videos. 3) Realistic Scans: The professional scanners support highquality object scans with precise shapes and realistic appearances. With the vast exploration space offered by OmniObject3D, we carefully set up four evaluation tracks: a) robust 3D perception, b) novel-view synthesis, c) neural surface reconstruction, and d) 3D object generation. Extensive studies are performed on these four benchmarks, revealing new observations, challenges, and opportunities for future research in realistic 3D vision.

Yiwen Chen, Chi Zhang, Xiaofeng Yang et al. · tencent-ai

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as over-saturation, inadequate detailing, and unrealistic outputs. This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images based on the renderings of coarse 3D models. Although the generated images mostly alleviate the aforementioned issues, challenges such as view inconsistency and significant content variance persist due to the inherent generative nature of large diffusion models, posing extensive difficulties in leveraging these images effectively. To overcome this hurdle, we advocate integrating a discriminator alongside a novel Diffusion-GAN dual training strategy to guide the training of 3D models. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data. We conduct a comprehensive set of experiments that demonstrate the effectiveness of our method over baseline approaches.

Xinyu Zhang, Li Wang, Jian Chen et al.

Radar has stronger adaptability in adverse scenarios for autonomous driving environmental perception compared to widely adopted cameras and LiDARs. Compared with commonly used 3D radars, the latest 4D radars have precise vertical resolution and higher point cloud density, making it a highly promising sensor for autonomous driving in complex environmental perception. However, due to the much higher noise than LiDAR, manufacturers choose different filtering strategies, resulting in an inverse ratio between noise level and point cloud density. There is still a lack of comparative analysis on which method is beneficial for deep learning-based perception algorithms in autonomous driving. One of the main reasons is that current datasets only adopt one type of 4D radar, making it difficult to compare different 4D radars in the same scene. Therefore, in this paper, we introduce a novel large-scale multi-modal dataset featuring, for the first time, two types of 4D radars captured simultaneously. This dataset enables further research into effective 4D radar perception algorithms.Our dataset consists of 151 consecutive series, most of which last 20 seconds and contain 10,007 meticulously synchronized and annotated frames. Moreover, our dataset captures a variety of challenging driving scenarios, including many road conditions, weather conditions, nighttime and daytime with different lighting intensities and periods. Our dataset annotates consecutive frames, which can be applied to 3D object detection and tracking, and also supports the study of multi-modal tasks. We experimentally validate our dataset, providing valuable results for studying different types of 4D radars. This dataset is released on https://github.com/adept-thu/Dual-Radar.

Hui En Pang, Zhongang Cai, Lei Yang et al.

3D human pose and shape estimation (a.k.a. "human mesh recovery") has achieved substantial progress. Researchers mainly focus on the development of novel algorithms, while less attention has been paid to other critical factors involved. This could lead to less optimal baselines, hindering the fair and faithful evaluations of newly designed methodologies. To address this problem, this work presents the first comprehensive benchmarking study from three under-explored perspectives beyond algorithms. 1) Datasets. An analysis on 31 datasets reveals the distinct impacts of data samples: datasets featuring critical attributes (i.e. diverse poses, shapes, camera characteristics, backbone features) are more effective. Strategical selection and combination of high-quality datasets can yield a significant boost to the model performance. 2) Backbones. Experiments with 10 backbones, ranging from CNNs to transformers, show the knowledge learnt from a proximity task is readily transferable to human mesh recovery. 3) Training strategies. Proper augmentation techniques and loss designs are crucial. With the above findings, we achieve a PA-MPJPE of 47.3 mm on the 3DPW test set with a relatively simple model. More importantly, we provide strong baselines for fair comparisons of algorithms, and recommendations for building effective training configurations in the future. Codebase is available at http://github.com/smplbody/hmr-benchmarks

Zhongang Cai, Wanqi Yin, Ailing Zeng et al.

Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion capture with numerous applications. Despite encouraging progress, current state-of-the-art methods still depend largely on a confined set of training datasets. In this work, we investigate scaling up EHPS towards the first generalist foundation model (dubbed SMPLer-X), with up to ViT-Huge as the backbone and training with up to 4.5M instances from diverse data sources. With big data and the large model, SMPLer-X exhibits strong performance across diverse test benchmarks and excellent transferability to even unseen environments. 1) For the data scaling, we perform a systematic investigation on 32 EHPS datasets, including a wide range of scenarios that a model trained on any single dataset cannot handle. More importantly, capitalizing on insights obtained from the extensive benchmarking process, we optimize our training scheme and select datasets that lead to a significant leap in EHPS capabilities. 2) For the model scaling, we take advantage of vision transformers to study the scaling law of model sizes in EHPS. Moreover, our finetuning strategy turn SMPLer-X into specialist models, allowing them to achieve further performance boosts. Notably, our foundation model SMPLer-X consistently delivers state-of-the-art results on seven benchmarks such as AGORA (107.2 mm NMVE), UBody (57.4 mm PVE), EgoBody (63.6 mm PVE), and EHF (62.3 mm PVE without finetuning). Homepage: https://caizhongang.github.io/projects/SMPLer-X/

Zhongang Cai, Daxuan Ren, Ailing Zeng et al.

4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications. With the advances of new sensors and algorithms, there is an increasing demand for more versatile datasets. In this work, we contribute HuMMan, a large-scale multi-modal 4D human dataset with 1000 human subjects, 400k sequences and 60M frames. HuMMan has several appealing properties: 1) multi-modal data and annotations including color images, point clouds, keypoints, SMPL parameters, and textured meshes; 2) popular mobile device is included in the sensor suite; 3) a set of 500 actions, designed to cover fundamental movements; 4) multiple tasks such as action recognition, pose estimation, parametric human recovery, and textured mesh reconstruction are supported and evaluated. Extensive experiments on HuMMan voice the need for further study on challenges such as fine-grained action recognition, dynamic human mesh reconstruction, point cloud-based parametric human recovery, and cross-device domain gaps.

Zhuguanyu Wu, Ruihao Gong, Yang Yong et al.

Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously evolving generator, making training costly when frequent updates are required, while reverse-KL-style matching can be mode-seeking and conservative for preserving strong motion dynamics. To address these issues, we propose \textbf{Score Gradient Matching Distillation (SGMD)}. SGMD adopts a fake-score perspective by directly optimizing the fake score toward the teacher, while using teacher stop-gradient Fisher as a stable distribution-matching objective. We provide a gradient analysis that motivates this objective choice under ideal tracking. Building on this, SGMD introduces a pair of dual potentials: negative-residual (NR) for outer-loop correction and residual-contraction (RC) for inner-loop tracking. Empirically, compared to DMD2, SGMD achieves an approximately $\sim 3\times$ training speedup and substantially improves motion dynamics for 4-step distilled models while preserving temporal consistency. A human study confirms that SGMD is preferred in motion quality and overall preference, while visual quality and text alignment remain comparable. Code is available at https://github.com/ModelTC/LightX2V.

Wei Cheng, Ruixiang Chen, Wanqi Yin et al.

Realistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather impoverished in terms of diversity, which are crucial for rendering effect. Researchers are usually constrained to explore and evaluate a small set of rendering problems on current datasets, while real-world applications require methods to be robust across different scenarios. In this work, we present DNA-Rendering, a large-scale, high-fidelity repository of human performance data for neural actor rendering. DNA-Rendering presents several alluring attributes. First, our dataset contains over 1500 human subjects, 5000 motion sequences, and 67.5M frames' data volume. Second, we provide rich assets for each subject -- 2D/3D human body keypoints, foreground masks, SMPLX models, cloth/accessory materials, multi-view images, and videos. These assets boost the current method's accuracy on downstream rendering tasks. Third, we construct a professional multi-view system to capture data, which contains 60 synchronous cameras with max 4096 x 3000 resolution, 15 fps speed, and stern camera calibration steps, ensuring high-quality resources for task training and evaluation. Along with the dataset, we provide a large-scale and quantitative benchmark in full-scale, with multiple tasks to evaluate the existing progress of novel view synthesis, novel pose animation synthesis, and novel identity rendering methods. In this manuscript, we describe our DNA-Rendering effort as a revealing of new observations, challenges, and future directions to human-centric rendering. The dataset, code, and benchmarks will be publicly available at https://dna-rendering.github.io/

Yuecheng Li, Jialong Chen, Chuan Chen et al.

Recently, nonnegative matrix factorization (NMF) has been widely adopted for community detection, because of its better interpretability. However, the existing NMF-based methods have the following three problems: 1) they directly transform the original network into community membership space, so it is difficult for them to capture the hierarchical information; 2) they often only pay attention to the topology of the network and ignore its node attributes; 3) it is hard for them to learn the global structure information necessary for community detection. Therefore, we propose a new community detection algorithm, named Contrastive Deep Nonnegative Matrix Factorization (CDNMF). Firstly, we deepen NMF to strengthen its capacity for information extraction. Subsequently, inspired by contrastive learning, our algorithm creatively constructs network topology and node attributes as two contrasting views. Furthermore, we utilize a debiased negative sampling layer and learn node similarity at the community level, thereby enhancing the suitability of our model for community detection. We conduct experiments on three public real graph datasets and the proposed model has achieved better results than state-of-the-art methods. Code available at https://github.com/6lyc/CDNMF.git.

Haonan Qiu, Zhaoxi Chen, Yuming Jiang et al.

Recent years have witnessed great progress in creating vivid audio-driven portraits from monocular videos. However, how to seamlessly adapt the created video avatars to other scenarios with different backgrounds and lighting conditions remains unsolved. On the other hand, existing relighting studies mostly rely on dynamically lighted or multi-view data, which are too expensive for creating video portraits. To bridge this gap, we propose ReliTalk, a novel framework for relightable audio-driven talking portrait generation from monocular videos. Our key insight is to decompose the portrait's reflectance from implicitly learned audio-driven facial normals and images. Specifically, we involve 3D facial priors derived from audio features to predict delicate normal maps through implicit functions. These initially predicted normals then take a crucial part in reflectance decomposition by dynamically estimating the lighting condition of the given video. Moreover, the stereoscopic face representation is refined using the identity-consistent loss under simulated multiple lighting conditions, addressing the ill-posed problem caused by limited views available from a single monocular video. Extensive experiments validate the superiority of our proposed framework on both real and synthetic datasets. Our code is released in https://github.com/arthur-qiu/ReliTalk.

Haiwen Diao, Jiahao Wang, Penghao Wu et al.

Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragments pixel-level signals across frames and scatters early pixel-word interactions. In parallel, native VLMs, despite impressive performance on single images, remain largely unexplored in multi-image, video understanding, and spatial intelligence. Hence, we introduce NEO-ov, a native foundation model that learns cross-frame and pixel-word correspondence end-to-end, without any external encoders, auxiliary adapters, or post-hoc fusion. By eliminating module boundaries entirely, NEO-ov enables fine-grained and unified spatiotemporal modeling to emerge natively inside the model. Notably, NEO-ov largely narrows the gap to modular counterparts while excelling at fine-grained visual perception, validating that native "one-vision" architectures are not only feasible but competitive at scale. Beyond empirical performance, we unveil systematic architectural analyses and detailed training recipes to facilitate subsequent native multimodal modeling. Our code and models are publicly available at: https://github.com/EvolvingLMMs-Lab/NEO.

Zhitao Yang, Zhongang Cai, Haiyi Mei et al.

Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets. To advance the diversity and annotation quality of human models, we introduce a new synthetic dataset, SynBody, with three appealing features: 1) a clothed parametric human model that can generate a diverse range of subjects; 2) the layered human representation that naturally offers high-quality 3D annotations to support multiple tasks; 3) a scalable system for producing realistic data to facilitate real-world tasks. The dataset comprises 1.2M images with corresponding accurate 3D annotations, covering 10,000 human body models, 1,187 actions, and various viewpoints. The dataset includes two subsets for human pose and shape estimation as well as human neural rendering. Extensive experiments on SynBody indicate that it substantially enhances both SMPL and SMPL-X estimation. Furthermore, the incorporation of layered annotations offers a valuable training resource for investigating the Human Neural Radiance Fields (NeRF).

Jiankun Li, Peisen Wang, Pengfei Xiong et al.

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by consumer-level devices like smartphones, due to practical complicating factors such as thin structures, non-ideal rectification, camera module inconsistencies and various hard-case scenes. In this paper, we propose a set of innovative designs to tackle the problem of practical stereo matching: 1) to better recover fine depth details, we design a hierarchical network with recurrent refinement to update disparities in a coarse-to-fine manner, as well as a stacked cascaded architecture for inference; 2) we propose an adaptive group correlation layer to mitigate the impact of erroneous rectification; 3) we introduce a new synthetic dataset with special attention to difficult cases for better generalizing to real-world scenes. Our results not only rank 1st on both Middlebury and ETH3D benchmarks, outperforming existing state-of-the-art methods by a notable margin, but also exhibit high-quality details for real-life photos, which clearly demonstrates the efficacy of our contributions.

Mingyuan Zhang, Zhongang Cai, Liang Pan et al.

Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent motion generation methods can directly generate human motions conditioned on natural languages. However, it remains challenging to achieve diverse and fine-grained motion generation with various text inputs. To address this problem, we propose MotionDiffuse, the first diffusion model-based text-driven motion generation framework, which demonstrates several desired properties over existing methods. 1) Probabilistic Mapping. Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected. 2) Realistic Synthesis. MotionDiffuse excels at modeling complicated data distribution and generating vivid motion sequences. 3) Multi-Level Manipulation. MotionDiffuse responds to fine-grained instructions on body parts, and arbitrary-length motion synthesis with time-varied text prompts. Our experiments show MotionDiffuse outperforms existing SoTA methods by convincing margins on text-driven motion generation and action-conditioned motion generation. A qualitative analysis further demonstrates MotionDiffuse's controllability for comprehensive motion generation. Homepage: https://mingyuan-zhang.github.io/projects/MotionDiffuse.html

Zhenguang Liu, Xinyang Yu, Ruili Wang et al.

The self-media era provides us tremendous high quality videos. Unfortunately, frequent video copyright infringements are now seriously damaging the interests and enthusiasm of video creators. Identifying infringing videos is therefore a compelling task. Current state-of-the-art methods tend to simply feed high-dimensional mixed video features into deep neural networks and count on the networks to extract useful representations. Despite its simplicity, this paradigm heavily relies on the original entangled features and lacks constraints guaranteeing that useful task-relevant semantics are extracted from the features. In this paper, we seek to tackle the above challenges from two aspects: (1) We propose to disentangle an original high-dimensional feature into multiple sub-features, explicitly disentangling the feature into exclusive lower-dimensional components. We expect the sub-features to encode non-overlapping semantics of the original feature and remove redundant information. (2) On top of the disentangled sub-features, we further learn an auxiliary feature to enhance the sub-features. We theoretically analyzed the mutual information between the label and the disentangled features, arriving at a loss that maximizes the extraction of task-relevant information from the original feature. Extensive experiments on two large-scale benchmark datasets (i.e., SVD and VCSL) demonstrate that our method achieves 90.1% TOP-100 mAP on the large-scale SVD dataset and also sets the new state-of-the-art on the VCSL benchmark dataset. Our code and model have been released at https://github.com/yyyooooo/DMI/, hoping to contribute to the community.

Weilin Wan, Lei Yang, Lingjie Liu et al.

Understanding human intentions during interactions has been a long-lasting theme, that has applications in human-robot interaction, virtual reality and surveillance. In this study, we focus on full-body human interactions with large-sized daily objects and aim to predict the future states of objects and humans given a sequential observation of human-object interaction. As there is no such dataset dedicated to full-body human interactions with large-sized daily objects, we collected a large-scale dataset containing thousands of interactions for training and evaluation purposes. We also observe that an object's intrinsic physical properties are useful for the object motion prediction, and thus design a set of object dynamic descriptors to encode such intrinsic properties. We treat the object dynamic descriptors as a new modality and propose a graph neural network, HO-GCN, to fuse motion data and dynamic descriptors for the prediction task. We show the proposed network that consumes dynamic descriptors can achieve state-of-the-art prediction results and help the network better generalize to unseen objects. We also demonstrate the predicted results are useful for human-robot collaborations.

Wenjia Wang, Yongtao Ge, Haiyi Mei et al.

As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body. The naive focal length assumptions can harm this task with the incorrectly formulated projection matrices. To solve this, we propose Zolly, the first 3DHMR method focusing on perspective-distorted images. Our approach begins with analysing the reason for perspective distortion, which we find is mainly caused by the relative location of the human body to the camera center. We propose a new camera model and a novel 2D representation, termed distortion image, which describes the 2D dense distortion scale of the human body. We then estimate the distance from distortion scale features rather than environment context features. Afterwards, we integrate the distortion feature with image features to reconstruct the body mesh. To formulate the correct projection matrix and locate the human body position, we simultaneously use perspective and weak-perspective projection loss. Since existing datasets could not handle this task, we propose the first synthetic dataset PDHuman and extend two real-world datasets tailored for this task, all containing perspective-distorted human images. Extensive experiments show that Zolly outperforms existing state-of-the-art methods on both perspective-distorted datasets and the standard benchmark (3DPW).

Yiwen Chen, Zilong Chen, Chi Zhang et al.

3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the other hand, methods based on implicit 3D representations, like Neural Radiance Field (NeRF), render complex scenes effectively but suffer from slow processing speeds and limited control over specific scene areas. In response to these challenges, our paper presents GaussianEditor, an innovative and efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation. GaussianEditor enhances precision and control in editing through our proposed Gaussian semantic tracing, which traces the editing target throughout the training process. Additionally, we propose Hierarchical Gaussian splatting (HGS) to achieve stabilized and fine results under stochastic generative guidance from 2D diffusion models. We also develop editing strategies for efficient object removal and integration, a challenging task for existing methods. Our comprehensive experiments demonstrate GaussianEditor's superior control, efficacy, and rapid performance, marking a significant advancement in 3D editing. Project Page: https://buaacyw.github.io/gaussian-editor/

Mingyuan Zhang, Xinying Guo, Liang Pan et al.

3D human motion generation is crucial for creative industry. Recent advances rely on generative models with domain knowledge for text-driven motion generation, leading to substantial progress in capturing common motions. However, the performance on more diverse motions remains unsatisfactory. In this work, we propose ReMoDiffuse, a diffusion-model-based motion generation framework that integrates a retrieval mechanism to refine the denoising process. ReMoDiffuse enhances the generalizability and diversity of text-driven motion generation with three key designs: 1) Hybrid Retrieval finds appropriate references from the database in terms of both semantic and kinematic similarities. 2) Semantic-Modulated Transformer selectively absorbs retrieval knowledge, adapting to the difference between retrieved samples and the target motion sequence. 3) Condition Mixture better utilizes the retrieval database during inference, overcoming the scale sensitivity in classifier-free guidance. Extensive experiments demonstrate that ReMoDiffuse outperforms state-of-the-art methods by balancing both text-motion consistency and motion quality, especially for more diverse motion generation.

Lei Yang, Siyu Ding, Deyi Xiong

Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation, question answering, and creative writing (CW), but training on one domain often degrades performance on others. Existing explanations based on catastrophic forgetting or global gradient conflict are incomplete: substantial interference can occur even when full-model gradients are nearly orthogonal. We show that single-domain RL produces sparse, small-magnitude parameter edits with weak overlap among top-changed neurons, while different domains still share substantial active computation routes on which update directions determine whether they act synergistically or conflict. Guided by this observation, we prove under a local perturbation model of multi-domain RL that later-domain training harms an earlier domain mainly through a second-order damage term, which under the observed sparse route structure concentrates in a low-dimensional shared conflict subspace. Moreover, a short domain refresh contracts the harmful component on this subspace, enabling selective recovery with limited collateral damage. Consistent with the theory, a brief Re-Math refresh after Code $\rightarrow$ Math $\rightarrow$ QA $\rightarrow$ CW recovers Math from 57.66 to 66.04 while largely preserving performance on the other domains, yielding the best average score of 66.39. Beyond refresh, a training-free rollback on a sparse proxy conflict coordinate set for the Math-QA pair partially restores Math, providing direct proxy-level evidence for localized damage. These results provide a localized mechanistic account of interference and recovery in multi-domain RL.

Lei Yang, Yalin Evren Sagduyu, Jason Hongjun Li et al.

We study adaptive network coding (NC) for scheduling real-time traffic over a single-hop wireless network. To meet the hard deadlines of real-time traffic, it is critical to strike a balance between maximizing the throughput and minimizing the risk that the entire block of coded packets may not be decodable by the deadline. Thus motivated, we explore adaptive NC, where the block size is adapted based on the remaining time to the deadline, by casting this sequential block size adaptation problem as a finite-horizon Markov decision process. One interesting finding is that the optimal block size and its corresponding action space monotonically decrease as the deadline approaches, and the optimal block size is bounded by the "greedy" block size. These unique structures make it possible to narrow down the search space of dynamic programming, building on which we develop a monotonicity-based backward induction algorithm (MBIA) that can solve for the optimal block size in polynomial time. Since channel erasure probabilities would be time-varying in a mobile network, we further develop a joint real-time scheduling and channel learning scheme with adaptive NC that can adapt to channel dynamics. We also generalize the analysis to multiple flows with hard deadlines and long-term delivery ratio constraints, devise a low-complexity online scheduling algorithm integrated with the MBIA, and then establish its asymptotical throughput-optimality. In addition to analysis and simulation results, we perform high fidelity wireless emulation tests with real radio transmissions to demonstrate the feasibility of the MBIA in finding the optimal block size in real time.

Sifeng He, Xudong Yang, Chen Jiang et al.

In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets restricted by either video-level annotation or small-scale, VCSL not only has two orders of magnitude more segment-level labelled data, with 160k realistic video copy pairs containing more than 280k localized copied segment pairs, but also covers a variety of video categories and a wide range of video duration. All the copied segments inside each collected video pair are manually extracted and accompanied by precisely annotated starting and ending timestamps. Alongside the dataset, we also propose a novel evaluation protocol that better measures the prediction accuracy of copy overlapping segments between a video pair and shows improved adaptability in different scenarios. By benchmarking several baseline and state-of-the-art segment-level video copy detection methods with the proposed dataset and evaluation metric, we provide a comprehensive analysis that uncovers the strengths and weaknesses of current approaches, hoping to open up promising directions for future works. The VCSL dataset, metric and benchmark codes are all publicly available at https://github.com/alipay/VCSL.

Xinshu Dong, Orfeas Stefanos Thyfronitis Litos, Ertem Nusret Tas et al.

The idea of security sharing goes back to Nakamoto's introduction of merge mining, a technique that enables Bitcoin miners to reuse their hash power to bootstrap and secure other Proof-of-Work (PoW) blockchains. However, with the rise of Proof-of-Stake (PoS) chains, there is a need for new methods of Bitcoin security sharing. We introduce Bitcoin staking, a protocol that allows Bitcoin holders to trustlessly use their idle asset to secure a PoS chain. The key challenge is to enable automatic slashing of bitcoins on the Bitcoin chain upon safety violations on the PoS chain. We achieve this using double-authentication-preventing signatures, finality gadgets and bi-directional timestamping between Bitcoin and the PoS chain. Our design is entirely modular and can be integrated with any PoS chain. A version of this protocol was deployed to secure the Babylon mainnet in April 2025 and currently has over 58,000 bitcoins staked (about 4 billion USD at current prices) while paying only 0.05% APR reward to the stakers. This is 2 orders of magnitude cheaper security cost than in PoS chains secured by their native token.

Zhongang Cai, Liang Pan, Chen Wei et al.

Human pose and shape estimation (HPS) has attracted increasing attention in recent years. While most existing studies focus on HPS from 2D images or videos with inherent depth ambiguity, there are surging need to investigate HPS from 3D point clouds as depth sensors have been frequently employed in commercial devices. However, real-world sensory 3D points are usually noisy and incomplete, and also human bodies could have different poses of high diversity. To tackle these challenges, we propose a principled framework, PointHPS, for accurate 3D HPS from point clouds captured in real-world settings, which iteratively refines point features through a cascaded architecture. Specifically, each stage of PointHPS performs a series of downsampling and upsampling operations to extract and collate both local and global cues, which are further enhanced by two novel modules: 1) Cross-stage Feature Fusion (CFF) for multi-scale feature propagation that allows information to flow effectively through the stages, and 2) Intermediate Feature Enhancement (IFE) for body-aware feature aggregation that improves feature quality after each stage. To facilitate a comprehensive study under various scenarios, we conduct our experiments on two large-scale benchmarks, comprising i) a dataset that features diverse subjects and actions captured by real commercial sensors in a laboratory environment, and ii) controlled synthetic data generated with realistic considerations such as clothed humans in crowded outdoor scenes. Extensive experiments demonstrate that PointHPS, with its powerful point feature extraction and processing scheme, outperforms State-of-the-Art methods by significant margins across the board. Homepage: https://caizhongang.github.io/projects/PointHPS/.

Bingqian Lin, Zicong Chen, Mingjie Li et al.

Medical artificial general intelligence (MAGI) enables one foundation model to solve different medical tasks, which is very practical in the medical domain. It can significantly reduce the requirement of large amounts of task-specific data by sufficiently sharing medical knowledge among different tasks. However, due to the challenges of designing strongly generalizable models with limited and complex medical data, most existing approaches tend to develop task-specific models. To take a step towards MAGI, we propose a new paradigm called Medical-knOwledge-enhanced mulTimOdal pretRaining (MOTOR). In MOTOR, we combine two kinds of basic medical knowledge, i.e., general and specific knowledge, in a complementary manner to boost the general pretraining process. As a result, the foundation model with comprehensive basic knowledge can learn compact representations from pretraining radiographic data for better cross-modal alignment. MOTOR unifies the understanding and generation, which are two kinds of core intelligence of an AI system, into a single medical foundation model, to flexibly handle more diverse medical tasks. To enable a comprehensive evaluation and facilitate further research, we construct a medical multimodal benchmark including a wide range of downstream tasks, such as chest x-ray report generation and medical visual question answering. Extensive experiments on our benchmark show that MOTOR obtains promising results through simple task-oriented adaptation. The visualization shows that the injected knowledge successfully highlights key information in the medical data, demonstrating the excellent interpretability of MOTOR. Our MOTOR successfully mimics the human practice of fulfilling a "medical student" to accelerate the process of becoming a "specialist". We believe that our work makes a significant stride in realizing MAGI.

Hong Guo, Yujing Wang, Jieyu Zhang et al. · microsoft-research, pku

Time-series anomaly detection is an important task and has been widely applied in the industry. Since manual data annotation is expensive and inefficient, most applications adopt unsupervised anomaly detection methods, but the results are usually sub-optimal and unsatisfactory to end customers. Weak supervision is a promising paradigm for obtaining considerable labels in a low-cost way, which enables the customers to label data by writing heuristic rules rather than annotating each instance individually. However, in the time-series domain, it is hard for people to write reasonable labeling functions as the time-series data is numerically continuous and difficult to be understood. In this paper, we propose a Label-Efficient Interactive Time-Series Anomaly Detection (LEIAD) system, which enables a user to improve the results of unsupervised anomaly detection by performing only a small amount of interactions with the system. To achieve this goal, the system integrates weak supervision and active learning collaboratively while generating labeling functions automatically using only a few labeled data. All of these techniques are complementary and can promote each other in a reinforced manner. We conduct experiments on three time-series anomaly detection datasets, demonstrating that the proposed system is superior to existing solutions in both weak supervision and active learning areas. Also, the system has been tested in a real scenario in industry to show its practicality.

Yakun Yu, Mingjun Zhao, Shi-ang Qi et al. · tencent-ai

Multimodal Sentiment Analysis leverages multimodal signals to detect the sentiment of a speaker. Previous approaches concentrate on performing multimodal fusion and representation learning based on general knowledge obtained from pretrained models, which neglects the effect of domain-specific knowledge. In this paper, we propose Contrastive Knowledge Injection (ConKI) for multimodal sentiment analysis, where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture. In addition, ConKI uses a hierarchical contrastive learning procedure performed between knowledge types within every single modality, across modalities within each sample, and across samples to facilitate the effective learning of the proposed representations, hence improving multimodal sentiment predictions. The experiments on three popular multimodal sentiment analysis benchmarks show that ConKI outperforms all prior methods on a variety of performance metrics.

Shoukang Hu, Fangzhou Hong, Liang Pan et al.

Existing Human NeRF methods for reconstructing 3D humans typically rely on multiple 2D images from multi-view cameras or monocular videos captured from fixed camera views. However, in real-world scenarios, human images are often captured from random camera angles, presenting challenges for high-quality 3D human reconstruction. In this paper, we propose SHERF, the first generalizable Human NeRF model for recovering animatable 3D humans from a single input image. SHERF extracts and encodes 3D human representations in canonical space, enabling rendering and animation from free views and poses. To achieve high-fidelity novel view and pose synthesis, the encoded 3D human representations should capture both global appearance and local fine-grained textures. To this end, we propose a bank of 3D-aware hierarchical features, including global, point-level, and pixel-aligned features, to facilitate informative encoding. Global features enhance the information extracted from the single input image and complement the information missing from the partial 2D observation. Point-level features provide strong clues of 3D human structure, while pixel-aligned features preserve more fine-grained details. To effectively integrate the 3D-aware hierarchical feature bank, we design a feature fusion transformer. Extensive experiments on THuman, RenderPeople, ZJU_MoCap, and HuMMan datasets demonstrate that SHERF achieves state-of-the-art performance, with better generalizability for novel view and pose synthesis.

Yilin Wen, Hao Pan, Lei Yang et al.

Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame pose and object information over a longer time span to recognize the action. Our approach achieves competitive results on two first-person hand action benchmarks, namely FPHA and H2O. Extensive ablation studies verify our design choices.

Fangzhou Hong, Mingyuan Zhang, Liang Pan et al.

3D avatar creation plays a crucial role in the digital age. However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technology to a larger audience, we propose AvatarCLIP, a zero-shot text-driven framework for 3D avatar generation and animation. Unlike professional software that requires expert knowledge, AvatarCLIP empowers layman users to customize a 3D avatar with the desired shape and texture, and drive the avatar with the described motions using solely natural languages. Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation. Specifically, driven by natural language descriptions, we initialize 3D human geometry generation with a shape VAE network. Based on the generated 3D human shapes, a volume rendering model is utilized to further facilitate geometry sculpting and texture generation. Moreover, by leveraging the priors learned in the motion VAE, a CLIP-guided reference-based motion synthesis method is proposed for the animation of the generated 3D avatar. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of AvatarCLIP on a wide range of avatars. Remarkably, AvatarCLIP can generate unseen 3D avatars with novel animations, achieving superior zero-shot capability.

Hao Guo, Kaixiang Xv, Ziwu Ge et al.

Collaborative edge computing uses edge nodes in different locations to execute tasks, necessitating dynamic task offloading decisions to maintain low latency and high reliability, especially under unpredictable node failures. Although deep reinforcement learning (DRL) and large language models (LLMs) have shown promise for task offloading, DRL often suffers from high sample inefficiency and local optima, whereas LLMs struggle with real-time decision-making. To address these limitations, we propose \textbf{LeDRL}, a hybrid decision framework that couples a \emph{lightweight LLM} with self-attention-enhanced DRL for real-time task offloading. LeDRL constructs structured, context-aware prompts capturing node status, task semantics, and link dynamics to derive high-level strategy priors. These are selectively processed by a self-attention-based alignment module for context-aware policy optimization. A reflective evaluator distills semantic feedback from past trajectories to guide future prompts, enabling more informative and temporally generalizable LLM queries. Extensive experiments show that LeDRL outperforms baselines in task success rate, convergence speed, and real-time responsiveness across diverse network scales, achieving over 17\% improvement in success rate. Furthermore, we deploy LeDRL on Jetson-based edge devices using our prototype system \textit{CoEdgeSys}, demonstrating its robustness and feasibility under resource constraints. Our code is available at:https://github.com/GalleyG5/LeDRL.git.

Anyi Rao, Xuekun Jiang, Yuwei Guo et al.

Amateurs working on mini-films and short-form videos usually spend lots of time and effort on the multi-round complicated process of setting and adjusting scenes, plots, and cameras to deliver satisfying video shots. We present Virtual Dynamic Storyboard (VDS) to allow users storyboarding shots in virtual environments, where the filming staff can easily test the settings of shots before the actual filming. VDS runs on a "propose-simulate-discriminate" mode: Given a formatted story script and a camera script as input, it generates several character animation and camera movement proposals following predefined story and cinematic rules to allow an off-the-shelf simulation engine to render videos. To pick up the top-quality dynamic storyboard from the candidates, we equip it with a shot ranking discriminator based on shot quality criteria learned from professional manual-created data. VDS is comprehensively validated via extensive experiments and user studies, demonstrating its efficiency, effectiveness, and great potential in assisting amateur video production.

Li Wang, Xinyu Zhang, Wenyuan Qin et al.

3D Multi-object tracking (MOT) ensures consistency during continuous dynamic detection, conducive to subsequent motion planning and navigation tasks in autonomous driving. However, camera-based methods suffer in the case of occlusions and it can be challenging to accurately track the irregular motion of objects for LiDAR-based methods. Some fusion methods work well but do not consider the untrustworthy issue of appearance features under occlusion. At the same time, the false detection problem also significantly affects tracking. As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection. For occlusion problems, we are the first to propose an occlusion head to select the best object appearance features multiple times effectively, reducing the influence of occlusions. To decrease the impact of false detection in tracking, we design a motion cost matrix based on confidence scores which improve the positioning and object prediction accuracy in 3D space. As existing multi-object tracking methods only consider a single category, we also propose to build a multi-category loss to implement multi-object tracking in multi-category scenes. A series of validation experiments are conducted on the KITTI and nuScenes tracking benchmarks. Our proposed method achieves state-of-the-art performance and the lowest identity switches (IDS) value (23 for Car and 137 for Pedestrian) among all multi-modal MOT methods on the KITTI test dataset. And our proposed method achieves state-of-the-art performance among all algorithms on the nuScenes test dataset with 75.3% AMOTA.

Lei Yang, Tao Tang, Jun Li et al.

While most recent autonomous driving system focuses on developing perception methods on ego-vehicle sensors, people tend to overlook an alternative approach to leverage intelligent roadside cameras to extend the perception ability beyond the visual range. We discover that the state-of-the-art vision-centric bird's eye view detection methods have inferior performances on roadside cameras. This is because these methods mainly focus on recovering the depth regarding the camera center, where the depth difference between the car and the ground quickly shrinks while the distance increases. In this paper, we propose a simple yet effective approach, dubbed BEVHeight++, to address this issue. In essence, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods. By incorporating both height and depth encoding techniques, we achieve a more accurate and robust projection from 2D to BEV spaces. On popular 3D detection benchmarks of roadside cameras, our method surpasses all previous vision-centric methods by a significant margin. In terms of the ego-vehicle scenario, our BEVHeight++ possesses superior over depth-only methods. Specifically, it yields a notable improvement of +1.9% NDS and +1.1% mAP over BEVDepth when evaluated on the nuScenes validation set. Moreover, on the nuScenes test set, our method achieves substantial advancements, with an increase of +2.8% NDS and +1.7% mAP, respectively.

Guanhua Wang, Heyang Qin, Sam Ade Jacobs et al.

Zero Redundancy Optimizer (ZeRO) has been used to train a wide range of large language models on massive GPUs clusters due to its ease of use, efficiency, and good scalability. However, when training on low-bandwidth clusters, or at scale which forces batch size per GPU to be small, ZeRO's effective throughput is limited because of high communication volume from gathering weights in forward pass, backward pass, and averaging gradients. This paper introduces three communication volume reduction techniques, which we collectively refer to as ZeRO++, targeting each of the communication collectives in ZeRO. First is block-quantization based all-gather. Second is data remapping that trades-off communication for more memory. Third is a novel all-to-all based quantized gradient averaging paradigm as replacement of reduce-scatter collective, which preserves accuracy despite communicating low precision data. Collectively, ZeRO++ reduces communication volume of ZeRO by 4x, enabling up to 2.16x better throughput at 384 GPU scale.

Xiangyu Fan, Jiaqi Li, Zhiqian Lin et al.

Audio-driven 3D facial animation aims to map input audio to realistic facial motion. Despite significant progress, limitations arise from inconsistent 3D annotations, restricting previous models to training on specific annotations and thereby constraining the training scale. In this work, we present UniTalker, a unified model featuring a multi-head architecture designed to effectively leverage datasets with varied annotations. To enhance training stability and ensure consistency among multi-head outputs, we employ three training strategies, namely, PCA, model warm-up, and pivot identity embedding. To expand the training scale and diversity, we assemble A2F-Bench, comprising five publicly available datasets and three newly curated datasets. These datasets contain a wide range of audio domains, covering multilingual speech voices and songs, thereby scaling the training data from commonly employed datasets, typically less than 1 hour, to 18.5 hours. With a single trained UniTalker model, we achieve substantial lip vertex error reductions of 9.2% for BIWI dataset and 13.7% for Vocaset. Additionally, the pre-trained UniTalker exhibits promise as the foundation model for audio-driven facial animation tasks. Fine-tuning the pre-trained UniTalker on seen datasets further enhances performance on each dataset, with an average error reduction of 6.3% on A2F-Bench. Moreover, fine-tuning UniTalker on an unseen dataset with only half the data surpasses prior state-of-the-art models trained on the full dataset. The code and dataset are available at the project page https://github.com/X-niper/UniTalker.

Feng Qian, Sifeng He, Honghao Huang et al.

With the growing popularity of smartphone photography in recent years, web photos play an increasingly important role in all walks of life. Source camera identification of web photos aims to establish a reliable linkage from the captured images to their source cameras, and has a broad range of applications, such as image copyright protection, user authentication, investigated evidence verification, etc. This paper presents an innovative and practical source identification framework that employs neural-network enhanced sensor pattern noise to trace back web photos efficiently while ensuring security. Our proposed framework consists of three main stages: initial device fingerprint registration, fingerprint extraction and cryptographic connection establishment while taking photos, and connection verification between photos and source devices. By incorporating metric learning and frequency consistency into the deep network design, our proposed fingerprint extraction algorithm achieves state-of-the-art performance on modern smartphone photos for reliable source identification. Meanwhile, we also propose several optimization sub-modules to prevent fingerprint leakage and improve accuracy and efficiency. Finally for practical system design, two cryptographic schemes are introduced to reliably identify the correlation between registered fingerprint and verified photo fingerprint, i.e. fuzzy extractor and zero-knowledge proof (ZKP). The codes for fingerprint extraction network and benchmark dataset with modern smartphone cameras photos are all publicly available at https://github.com/PhotoNecf/PhotoNecf.

Lei Yang, Jiaxin Yu, Xinyu Zhang et al.

Although the majority of recent autonomous driving systems concentrate on developing perception methods based on ego-vehicle sensors, there is an overlooked alternative approach that involves leveraging intelligent roadside cameras to help extend the ego-vehicle perception ability beyond the visual range. We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground. However, the roadside camera is installed on a pole with a pitched angle, which makes the existing methods not optimal for roadside scenes. In this paper, we introduce a novel framework for Roadside Monocular 3D object detection with ground-aware embeddings, named MonoGAE. Specifically, the ground plane is a stable and strong prior knowledge due to the fixed installation of cameras in roadside scenarios. In order to reduce the domain gap between the ground geometry information and high-dimensional image features, we employ a supervised training paradigm with a ground plane to predict high-dimensional ground-aware embeddings. These embeddings are subsequently integrated with image features through cross-attention mechanisms. Furthermore, to improve the detector's robustness to the divergences in cameras' installation poses, we replace the ground plane depth map with a novel pixel-level refined ground plane equation map. Our approach demonstrates a substantial performance advantage over all previous monocular 3D object detectors on widely recognized 3D detection benchmarks for roadside cameras. The code and pre-trained models will be released soon.

Yi Sheng, Junhuan Yang, Lei Yang et al.

Model fairness (a.k.a., bias) has become one of the most critical problems in a wide range of AI applications. An unfair model in autonomous driving may cause a traffic accident if corner cases (e.g., extreme weather) cannot be fairly regarded; or it will incur healthcare disparities if the AI model misdiagnoses a certain group of people (e.g., brown and black skin). In recent years, there have been emerging research works on addressing unfairness, and they mainly focus on a single unfair attribute, like skin tone; however, real-world data commonly have multiple attributes, among which unfairness can exist in more than one attribute, called 'multi-dimensional fairness'. In this paper, we first reveal a strong correlation between the different unfair attributes, i.e., optimizing fairness on one attribute will lead to the collapse of others. Then, we propose a novel Multi-Dimension Fairness framework, namely Muffin, which includes an automatic tool to unite off-the-shelf models to improve the fairness on multiple attributes simultaneously. Case studies on dermatology datasets with two unfair attributes show that the existing approach can achieve 21.05% fairness improvement on the first attribute while it makes the second attribute unfair by 1.85%. On the other hand, the proposed Muffin can unite multiple models to achieve simultaneously 26.32% and 20.37% fairness improvement on both attributes; meanwhile, it obtains 5.58% accuracy gain.

Shoukang Hu, Fangzhou Hong, Tao Hu et al.

3D human generation from 2D images has achieved remarkable progress through the synergistic utilization of neural rendering and generative models. Existing 3D human generative models mainly generate a clothed 3D human as an undetectable 3D model in a single pass, while rarely considering the layer-wise nature of a clothed human body, which often consists of the human body and various clothes such as underwear, outerwear, trousers, shoes, etc. In this work, we propose HumanLiff, the first layer-wise 3D human generative model with a unified diffusion process. Specifically, HumanLiff firstly generates minimal-clothed humans, represented by tri-plane features, in a canonical space, and then progressively generates clothes in a layer-wise manner. In this way, the 3D human generation is thus formulated as a sequence of diffusion-based 3D conditional generation. To reconstruct more fine-grained 3D humans with tri-plane representation, we propose a tri-plane shift operation that splits each tri-plane into three sub-planes and shifts these sub-planes to enable feature grid subdivision. To further enhance the controllability of 3D generation with 3D layered conditions, HumanLiff hierarchically fuses tri-plane features and 3D layered conditions to facilitate the 3D diffusion model learning. Extensive experiments on two layer-wise 3D human datasets, SynBody (synthetic) and TightCap (real-world), validate that HumanLiff significantly outperforms state-of-the-art methods in layer-wise 3D human generation. Our code will be available at https://skhu101.github.io/HumanLiff.

Yawen Wu, Dewen Zeng, Zhepeng Wang et al.

In dermatological disease diagnosis, the private data collected by mobile dermatology assistants exist on distributed mobile devices of patients. Federated learning (FL) can use decentralized data to train models while keeping data local. Existing FL methods assume all the data have labels. However, medical data often comes without full labels due to high labeling costs. Self-supervised learning (SSL) methods, contrastive learning (CL) and masked autoencoders (MAE), can leverage the unlabeled data to pre-train models, followed by fine-tuning with limited labels. However, combining SSL and FL has unique challenges. For example, CL requires diverse data but each device only has limited data. For MAE, while Vision Transformer (ViT) based MAE has higher accuracy over CNNs in centralized learning, MAE's performance in FL with unlabeled data has not been investigated. Besides, the ViT synchronization between the server and clients is different from traditional CNNs. Therefore, special synchronization methods need to be designed. In this work, we propose two federated self-supervised learning frameworks for dermatological disease diagnosis with limited labels. The first one features lower computation costs, suitable for mobile devices. The second one features high accuracy and fits high-performance servers. Based on CL, we proposed federated contrastive learning with feature sharing (FedCLF). Features are shared for diverse contrastive information without sharing raw data for privacy. Based on MAE, we proposed FedMAE. Knowledge split separates the global and local knowledge learned from each client. Only global knowledge is aggregated for higher generalization performance. Experiments on dermatological disease datasets show superior accuracy of the proposed frameworks over state-of-the-arts.

Zhongfei Qing, Zhongang Cai, Zhitao Yang et al.

Generating natural human motion from a story has the potential to transform the landscape of animation, gaming, and film industries. A new and challenging task, Story-to-Motion, arises when characters are required to move to various locations and perform specific motions based on a long text description. This task demands a fusion of low-level control (trajectories) and high-level control (motion semantics). Previous works in character control and text-to-motion have addressed related aspects, yet a comprehensive solution remains elusive: character control methods do not handle text description, whereas text-to-motion methods lack position constraints and often produce unstable motions. In light of these limitations, we propose a novel system that generates controllable, infinitely long motions and trajectories aligned with the input text. (1) We leverage contemporary Large Language Models to act as a text-driven motion scheduler to extract a series of (text, position, duration) pairs from long text. (2) We develop a text-driven motion retrieval scheme that incorporates motion matching with motion semantic and trajectory constraints. (3) We design a progressive mask transformer that addresses common artifacts in the transition motion such as unnatural pose and foot sliding. Beyond its pioneering role as the first comprehensive solution for Story-to-Motion, our system undergoes evaluation across three distinct sub-tasks: trajectory following, temporal action composition, and motion blending, where it outperforms previous state-of-the-art motion synthesis methods across the board. Homepage: https://story2motion.github.io/.

Junhuan Yang, Yi Sheng, Yuzhou Zhang et al.

Along with the breakthrough of convolutional neural networks, learning-based segmentation has emerged in many research works. Most of them are based on supervised learning, requiring plenty of annotated data; however, to support segmentation, a label for each pixel is required, which is obviously expensive. As a result, the issue of lacking annotated segmentation data commonly exists. Continuous learning is a promising way to deal with this issue; however, it still has high demands on human labor for annotation. What's more, privacy is highly required in segmentation data for real-world applications, which further calls for on-device learning. In this paper, we aim to resolve the above issue in an alternative way: Instead of supervised segmentation, we propose to develop efficient unsupervised segmentation that can be executed on edge devices. Based on our observation that segmentation can obtain high performance when pixels are mapped to a high-dimension space, we for the first time bring brain-inspired hyperdimensional computing (HDC) to the segmentation task. We build the HDC-based unsupervised segmentation framework, namely "SegHDC". In SegHDC, we devise a novel encoding approach that follows the Manhattan distance. A clustering algorithm is further developed on top of the encoded high-dimension vectors to obtain segmentation results. Experimental results show SegHDC can significantly surpass neural network-based unsupervised segmentation. On a standard segmentation dataset, DSB2018, SegHDC can achieve a 28.0% improvement in Intersection over Union (IoU) score; meanwhile, it achieves over 300x speedup on Raspberry PI. What's more, for a larger size image in the BBBC005 dataset, the existing approach cannot be accommodated to Raspberry PI due to out of memory; on the other hand, SegHDC can obtain segmentation results within 3 minutes while achieving a 0.9587 IoU score.

Hui En Pang, Shuai Liu, Zhongang Cai et al.

We present \textbf{Disco4D}, a novel Gaussian Splatting framework for 4D human generation and animation from a single image. Different from existing methods, Disco4D distinctively disentangles clothings (with Gaussian models) from the human body (with SMPL-X model), significantly enhancing the generation details and flexibility. It has the following technical innovations. \textbf{1)} Disco4D learns to efficiently fit the clothing Gaussians over the SMPL-X Gaussians. \textbf{2)} It adopts diffusion models to enhance the 3D generation process, \textit{e.g.}, modeling occluded parts not visible in the input image. \textbf{3)} It learns an identity encoding for each clothing Gaussian to facilitate the separation and extraction of clothing assets. Furthermore, Disco4D naturally supports 4D human animation with vivid dynamics. Extensive experiments demonstrate the superiority of Disco4D on 4D human generation and animation tasks. Our visualizations can be found in \url{https://disco-4d.github.io/}.