Ming Zeng

Xiaoyi Dong, Jianmin Bao, Yinglin Zheng et al.

This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core idea of masked self-distillation is to distill representation from a full image to the representation predicted from a masked image. Such incorporation enjoys two vital benefits. First, masked self-distillation targets local patch representation learning, which is complementary to vision-language contrastive focusing on text-related representation. Second, masked self-distillation is also consistent with vision-language contrastive from the perspective of training objective as both utilize the visual encoder for feature aligning, and thus is able to learn local semantics getting indirect supervision from the language. We provide specially designed experiments with a comprehensive analysis to validate the two benefits. Symmetrically, we also introduce the local semantic supervision into the text branch, which further improves the pretraining performance. With extensive experiments, we show that MaskCLIP, when applied to various challenging downstream tasks, achieves superior results in linear probing, finetuning, and zero-shot performance with the guidance of the language encoder. Code will be release at \url{https://github.com/LightDXY/MaskCLIP}.

Huidong Feng, Wentao Chen, Jie Chen et al.

With the rapid advancement of artificial intelligence generated content (AIGC) technologies, video forgery has become increasingly prevalent, posing new challenges to public discourse and societal security. Despite remarkable progress in existing deepfake detection methods, AIGC forgery detection remains challenging, as existing datasets mainly rely on open-source video generation models with quality far below that of commercial AIGC systems. Even datasets containing a few commercial samples often retain visible watermarks, compromising authenticity and hindering model generalization to high-fidelity AIGC videos. To address these issues, we introduce CoCoVideo-26K, a contrastive, commercial-model-based AIGC video dataset covering 13 mainstream commercial generators and providing semantically aligned real-fake video pairs. This dataset enables deeper exploration of the differences between authentic and high-quality synthetic videos and establishes a new benchmark for highly realistic video forgery detection. Building on this dataset, we propose CoCoDetect, a detection framework integrating contrastive learning with confidence-gated multimodal large language model (MLLM) inference. An R3D-18 backbone extracts spatio-temporal representations, while a confidence gate routes uncertain cases to an MLLM for reasoning about physical plausibility and scene consistency. Extensive experiments on CoCoVideo-26K and public benchmarks demonstrate state-of-the-art performance, validating the framework's robustness and generalizability. Our code and dataset are available at https://github.com/DonoToT/CoCoVideo.

Mingyi Xu, Jinpeng Lin, Min Zhou et al.

Scribble-guided image editing allows users to combine simple scribble annotations with text prompts to specify both where and how an image should be edited, enabling flexible interaction with precise spatial control. However, existing models still exhibit unstable performance under this paradigm, especially in multi-task scenarios. To improve performance, we conduct empirical studies using an open-source editing model and reveal an asymmetry in generalization: instruction-level generalization, including across editing tasks and from single-task to multi-task settings, is more challenging than image-domain generalization, such as from synthetic to real-world images or from mosaicked to regular images. This suggests that the primary bottleneck lies in insufficient learning for diverse editing instructions rather than in the image domain gap. Motivated by this insight, we propose three strategies: (a) a Coverage-then-Realism Curriculum, a two-stage pipeline that first builds large-scale synthetic, instruction-rich data for broad task supervision, then curates a small set of real-world data to refine generation realism; (b) Multi-Task Mosaicking, which constructs multi-task training samples by concatenating single-task examples at nearly zero cost while enabling the learned capability to generalize to non-mosaicked images; and (c) an Edit-Focused Loss, which leverages the changed regions between input and output images in synthetic data to focus training on edited regions, improving both learning efficiency and editing accuracy. With these strategies, we substantially improve both single-task and multi-task scribble-guided editing on the VIBE benchmark, achieving state-of-the-art results. We will publicly release our dataset and model.

Yiwei Ding, Wenjin Deng, Yinglin Zheng et al.

In this paper, we present the Intra- and Inter-Human Relation Networks (I^2R-Net) for Multi-Person Pose Estimation. It involves two basic modules. First, the Intra-Human Relation Module operates on a single person and aims to capture Intra-Human dependencies. Second, the Inter-Human Relation Module considers the relation between multiple instances and focuses on capturing Inter-Human interactions. The Inter-Human Relation Module can be designed very lightweight by reducing the resolution of feature map, yet learn useful relation information to significantly boost the performance of the Intra-Human Relation Module. Even without bells and whistles, our method can compete or outperform current competition winners. We conduct extensive experiments on COCO, CrowdPose, and OCHuman datasets. The results demonstrate that the proposed model surpasses all the state-of-the-art methods. Concretely, the proposed method achieves 77.4% AP on CrowPose dataset and 67.8% AP on OCHuman dataset respectively, outperforming existing methods by a large margin. Additionally, the ablation study and visualization analysis also prove the effectiveness of our model.

Pengfei Liu, Wenjin Deng, Hengda Li et al.

It is still an interesting and challenging problem to synthesize a vivid and realistic singing face driven by music signal. In this paper, we present a method for this task with natural motions of the lip, facial expression, head pose, and eye states. Due to the coupling of the mixed information of human voice and background music in common signals of music audio, we design a decouple-and-fuse strategy to tackle the challenge. We first decompose the input music audio into human voice stream and background music stream. Due to the implicit and complicated correlation between the two-stream input signals and the dynamics of the facial expressions, head motions and eye states, we model their relationship with an attention scheme, where the effects of the two streams are fused seamlessly. Furthermore, to improve the expressiveness of the generated results, we propose to decompose head movements generation into speed generation and direction generation, and decompose eye states generation into the short-time eye blinking generation and the long-time eye closing generation to model them separately. We also build a novel SingingFace Dataset to support the training and evaluation of this task, and to facilitate future works on this topic. Extensive experiments and user study show that our proposed method is capable of synthesizing vivid singing face, which is better than state-of-the-art methods qualitatively and quantitatively.

Ji Wang, Hao Chen, Yixuan Li et al.

This paper investigates a rotatable antenna (RA) assisted mobile edge computing (MEC) network, where multiple users offload their computation tasks to an edge server equipped with an RA array under a time-division multiple access protocol. To maximize the weighted sum computation rate, we formulate a joint optimization problem over the RA rotation angles, time-slot allocation, transmit power, and local CPU frequencies. Due to the non-convex nature of the formulated problem, a scenario-adaptive hybrid optimization algorithm is proposed. Specifically, for the dynamic rotating scenario, where RAs can flexibly reorient within each time slot, we derive closed-form optimal antenna pointing vectors to enable a low-complexity sequential solution. In contrast, for the static rotating scenario where RAs maintain a unified orientation, we develop an alternating optimization framework, where the non-convex RA rotation constraints are handled using successive convex approximation iteratively with the resource allocation. Simulation results demonstrate that the proposed RA assisted MEC network significantly outperforms conventional fixed-antenna MEC networks. Owing to the additional spatial degrees of freedom introduced by mechanical rotation, the flexibility of RAs effectively mitigates the severe beam misalignment inherent in fixed-antenna systems, particularly under high antenna directivity.

Ming Zeng, Ji Wang, Wanming Hao et al.

Extremely large-scale multiple-input multiple-output (XL-MIMO) is a key technology for next-generation wireless communication systems. By deploying significantly more antennas than conventional massive MIMO systems, XL-MIMO promises substantial improvements in spectral efficiency. However, due to the drastically increased array size, the conventional planar wave channel model is no longer accurate, necessitating a transition to a near-field spherical wave model. This shift challenges traditional beam training and channel estimation methods, which were designed for planar wave propagation. In this article, we present a comprehensive review of state-of-the-art beam training and channel estimation techniques for XL-MIMO systems. We analyze the fundamental principles, key methodologies, and recent advancements in this area, highlighting their respective strengths and limitations in addressing the challenges posed by the near-field propagation environment. Furthermore, we explore open research challenges that remain unresolved to provide valuable insights for researchers and engineers working toward the development of next-generation XL-MIMO communication systems.

Jian Xiao, Ji Wang, Ming Zeng et al.

A model-driven deep learning framework is proposed for channel estimation in Rydberg atomic quantum receivers (RAQRs) based on the measurement of holographic snapshots. Specifically, we develop a Transformer-based unrolling architecture, termed URformer, to solve the non-linear biased phase retrieval problem, which is derived by unrolling a stabilized variant of the expectation-maximization Gerchberg-Saxton (EM-GS) algorithm. Each layer of the proposed URformer incorporates three trainable modules: 1) a learnable filter network that replaces the fixed Bessel kernel in the classic EM-GS algorithm; 2) a trainable gating mechanism that adaptively combines classic updates to ensure training stability; and 3) an efficient channel Transformer module that learns to correct residual errors by capturing non-local channel dependencies. Numerical results demonstrate that the proposed URformer significantly outperforms classic iterative algorithms and conventional black-box neural networks with less pilot overhead.

Hao Feng, Ebrahim Bedeer, Ming Zeng et al.

Pinching antenna (PA) systems have recently emerged as a promising architecture for reconfigurable wireless communications by enabling flexible antenna placement along a dielectric waveguide. However, existing works typically assume perfect knowledge of user locations, which is impractical in real systems where location estimation errors are inevitable. In this paper, we investigate robust power allocation and antenna placement for PA systems under user location uncertainty. We consider both single-antenna and multi-antenna configurations, where the true user locations are unknown but lie within bounded uncertainty regions. For the single-antenna case, we adopt a worst-case robust design and leverage the S-procedure to transform the joint power allocation and antenna placement problem into a convex semidefinite program (SDP), ensuring that quality-of-service (QoS) constraints are satisfied for all possible user locations. For the multi-antenna case, we address the additional challenges arising from the superposition of channel components from multiple antennas by developing an efficient numerical procedure to evaluate the worst-case channel gain. Then, we derive a closed-form solution for optimal power allocation and develop a block coordinate descent algorithm to optimize antenna placement. Simulation results show that the proposed framework provides robustness to location uncertainty while achieving power consumption close to that of outage-based benchmark schemes.

Honggu Zhou, Xiaogang Peng, Jiawei Mao et al.

Some self-supervised cross-modal learning approaches have recently demonstrated the potential of image signals for enhancing point cloud representation. However, it remains a question on how to directly model cross-modal local and global correspondences in a self-supervised fashion. To solve it, we proposed PointCMC, a novel cross-modal method to model multi-scale correspondences across modalities for self-supervised point cloud representation learning. In particular, PointCMC is composed of: (1) a local-to-local (L2L) module that learns local correspondences through optimized cross-modal local geometric features, (2) a local-to-global (L2G) module that aims to learn the correspondences between local and global features across modalities via local-global discrimination, and (3) a global-to-global (G2G) module, which leverages auxiliary global contrastive loss between the point cloud and image to learn high-level semantic correspondences. Extensive experiment results show that our approach outperforms existing state-of-the-art methods in various downstream tasks such as 3D object classification and segmentation. Code will be made publicly available upon acceptance.

Chao Chen, Chenghua Guo, Rufeng Chen et al.

To foster trust in machine learning models, explanations must be faithful and stable for consistent insights. Existing relevant works rely on the $\ell_p$ distance for stability assessment, which diverges from human perception. Besides, existing adversarial training (AT) associated with intensive computations may lead to an arms race. To address these challenges, we introduce a novel metric to assess the stability of top-$k$ salient features. We introduce R2ET which trains for stable explanation by efficient and effective regularizer, and analyze R2ET by multi-objective optimization to prove numerical and statistical stability of explanations. Moreover, theoretical connections between R2ET and certified robustness justify R2ET's stability in all attacks. Extensive experiments across various data modalities and model architectures show that R2ET achieves superior stability against stealthy attacks, and generalizes effectively across different explanation methods.

Fenglin Liu, Zheng Li, Hongjian Zhou et al.

The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering (QA) task with answer options for evaluation. However, many clinical decisions involve answering open-ended questions without pre-set options. To better understand LLMs in the clinic, we construct a benchmark ClinicBench. We first collect eleven existing datasets covering diverse clinical language generation, understanding, and reasoning tasks. Furthermore, we construct six novel datasets and clinical tasks that are complex but common in real-world practice, e.g., open-ended decision-making, long document processing, and emerging drug analysis. We conduct an extensive evaluation of twenty-two LLMs under both zero-shot and few-shot settings. Finally, we invite medical experts to evaluate the clinical usefulness of LLMs. The benchmark data is available at https://github.com/AI-in-Health/ClinicBench.

Chao Chen, Chenghua Guo, Guixiang Ma et al.

Robust explanations of machine learning models are critical to establish human trust in the models. Due to limited cognition capability, most humans can only interpret the top few salient features. It is critical to make top salient features robust to adversarial attacks, especially those against the more vulnerable gradient-based explanations. Existing defense measures robustness using $\ell_p$-norms, which have weaker protection power. We define explanation thickness for measuring salient features ranking stability, and derive tractable surrogate bounds of the thickness to design the \textit{R2ET} algorithm to efficiently maximize the thickness and anchor top salient features. Theoretically, we prove a connection between R2ET and adversarial training. Experiments with a wide spectrum of network architectures and data modalities, including brain networks, demonstrate that R2ET attains higher explanation robustness under stealthy attacks while retaining accuracy.

Zhaoxuan Tan, Zheng Li, Tianyi Liu et al.

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. In this work, we present PUGC, a novel framework that leverages implicit human Preferences in unlabeled User-Generated Content (UGC) to generate preference data. Although UGC is not explicitly created to guide LLMs in generating human-preferred responses, it often reflects valuable insights and implicit preferences from its creators that has the potential to address readers' questions. PUGC transforms UGC into user queries and generates responses from the policy model. The UGC is then leveraged as a reference text for response scoring, aligning the model with these implicit preferences. This approach improves the quality of preference data while enabling scalable, domain-specific alignment. Experimental results on Alpaca Eval 2 show that models trained with DPO and PUGC achieve a 9.37% performance improvement over traditional methods, setting a 35.93% state-of-the-art length-controlled win rate using Mistral-7B-Instruct. Further studies highlight gains in reward quality, domain-specific alignment effectiveness, robustness against UGC quality, and theory of mind capabilities. Our code and dataset are available at https://zhaoxuan.info/PUGC.github.io/

Xiangjun Zhang, Litong Gong, Yinglin Zheng et al.

Most text-to-video(T2V) diffusion models depend on pre-trained text encoders for semantic alignment, yet they often fail to maintain video quality when provided with concise prompts rather than well-designed ones. The primary issue lies in their limited textual semantics understanding. Moreover, these text encoders cannot rephrase prompts online to better align with user intentions, which limits both the scalability and usability of the models, To address these challenges, we introduce RISE-T2V, which uniquely integrates the processes of prompt rephrasing and semantic feature extraction into a single and seamless step instead of two separate steps. RISE-T2V is universal and can be applied to various pre-trained LLMs and video diffusion models(VDMs), significantly enhancing their capabilities for T2V tasks. We propose an innovative module called the Rephrasing Adapter, enabling diffusion models to utilize text hidden states during the next token prediction of the LLM as a condition for video generation. By employing a Rephrasing Adapter, the video generation model can implicitly rephrase basic prompts into more comprehensive representations that better match the user's intent. Furthermore, we leverage the powerful capabilities of LLMs to enable video generation models to accomplish a broader range of T2V tasks. Extensive experiments demonstrate that RISE-T2V is a versatile framework applicable to different video diffusion model architectures, significantly enhancing the ability of T2V models to generate high-quality videos that align with user intent. Visual results are available on the webpage at https://rise-t2v.github.io.

Jing Yang Lee, Hamed Bonab, Nasser Zalmout et al.

Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potential mismatch between required capabilities and training paradigms. We introduce a novel approach to address this discrepancy by synthesizing conversational data from existing text corpora. We present a pipeline that transforms a cluster of multiple related documents into an extended multi-turn, multi-topic information-seeking dialogue. Applying our pipeline to Wikipedia articles, we curate DocTalk, a multi-turn pre-training dialogue corpus consisting of over 730k long conversations. We hypothesize that exposure to such synthesized conversational structures during pre-training can enhance the fundamental multi-turn capabilities of LLMs, such as context memory and understanding. Empirically, we show that incorporating DocTalk during pre-training results in up to 40% gain in context memory and understanding, without compromising base performance. DocTalk is available at https://huggingface.co/datasets/AmazonScience/DocTalk.

Renshuai Liu, Chengyang Li, Haitao Cao et al.

Although remarkable progress has been made in recent years, current multi-exposure image fusion (MEF) research is still bounded by the lack of real ground truth, objective evaluation function, and robust fusion strategy. In this paper, we study the MEF problem from a new perspective. We don't utilize any synthesized ground truth, design any loss function, or develop any fusion strategy. Our proposed method EMEF takes advantage of the wisdom of multiple imperfect MEF contributors including both conventional and deep learning-based methods. Specifically, EMEF consists of two main stages: pre-train an imitator network and tune the imitator in the runtime. In the first stage, we make a unified network imitate different MEF targets in a style modulation way. In the second stage, we tune the imitator network by optimizing the style code, in order to find an optimal fusion result for each input pair. In the experiment, we construct EMEF from four state-of-the-art MEF methods and then make comparisons with the individuals and several other competitive methods on the latest released MEF benchmark dataset. The promising experimental results demonstrate that our ensemble framework can "get the best of all worlds". The code is available at https://github.com/medalwill/EMEF.

Jianpeng Chen, Yujing Wang, Ming Zeng et al.

Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not always effective. Intuitively, paths in a graph imply different semantics for different downstream tasks. Inspired by this, we design a novel GNN solution, namely Customized Graph Neural Network with Path Reweighting (CustomGNN for short). Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph. Furthermore, we empirically analyze the semantics learned by CustomGNN and demonstrate its ability to avoid the three inherent problems in traditional GNNs, i.e., over-smoothing, poor robustness, and overfitting. In experiments with the node classification task, CustomGNN achieves state-of-the-art accuracies on three standard graph datasets and four large graph datasets. The source code of the proposed CustomGNN is available at \url{https://github.com/cjpcool/CustomGNN}.

Chengrui Wang, Pengfei Liu, Min Zhou et al.

Although diffusion models can generate high-quality human images, their applications are limited by the instability in generating hands with correct structures. In this paper, we introduce RHanDS, a conditional diffusion-based framework designed to refine malformed hands by utilizing decoupled structure and style guidance. The hand mesh reconstructed from the malformed hand offers structure guidance for correcting the structure of the hand, while the malformed hand itself provides style guidance for preserving the style of the hand. To alleviate the mutual interference between style and structure guidance, we introduce a two-stage training strategy and build a series of multi-style hand datasets. In the first stage, we use paired hand images for training to ensure stylistic consistency in hand refining. In the second stage, various hand images generated based on human meshes are used for training, enabling the model to gain control over the hand structure. Experimental results demonstrate that RHanDS can effectively refine hand structure while preserving consistency in hand style.

Zizhao Wu, Jian Shi, Xuan Deng et al.

Point cloud completion aims to infer a complete shape from its partial observation. Many approaches utilize a pure encoderdecoder paradigm in which complete shape can be directly predicted by shape priors learned from partial scans, however, these methods suffer from the loss of details inevitably due to the feature abstraction issues. In this paper, we propose a novel framework,termed SPAC-Net, that aims to rethink the completion task under the guidance of a new structural prior, we call it interface. Specifically, our method first investigates Marginal Detector (MAD) module to localize the interface, defined as the intersection between the known observation and the missing parts. Based on the interface, our method predicts the coarse shape by learning the displacement from the points in interface move to their corresponding position in missing parts. Furthermore, we devise an additional Structure Supplement(SSP) module before the upsampling stage to enhance the structural details of the coarse shape, enabling the upsampling module to focus more on the upsampling task. Extensive experiments have been conducted on several challenging benchmarks, and the results demonstrate that our method outperforms existing state-of-the-art approaches.

Bibo Wu, Fang Fang, Ming Zeng et al.

Leveraging pinching antennas in wireless network enabled federated learning (FL) can effectively mitigate the common "straggler" issue in FL by dynamically establishing strong line-of-sight (LoS) links on demand. This letter proposes a hybrid conventional and pinching antenna network (HCPAN) to significantly improve communication efficiency in the non-orthogonal multiple access (NOMA)-enabled FL system. Within this framework, a fuzzy logic-based client classification scheme is first proposed to effectively balance clients' data contributions and communication conditions. Given this classification, we formulate a total time minimization problem to jointly optimize pinching antenna placement and resource allocation. Due to the complexity of variable coupling and non-convexity, a deep reinforcement learning (DRL)-based algorithm is developed to effectively address this problem. Simulation results validate the superiority of the proposed scheme in enhancing FL performance via the optimized deployment of pinching antenna.

Yuxin Lin, Yinglin Zheng, Ming Zeng et al.

This paper addresses the gap in predicting turn-taking and backchannel actions in human-machine conversations using multi-modal signals (linguistic, acoustic, and visual). To overcome the limitation of existing datasets, we propose an automatic data collection pipeline that allows us to collect and annotate over 210 hours of human conversation videos. From this, we construct a Multi-Modal Face-to-Face (MM-F2F) human conversation dataset, including over 1.5M words and corresponding turn-taking and backchannel annotations from approximately 20M frames. Additionally, we present an end-to-end framework that predicts the probability of turn-taking and backchannel actions from multi-modal signals. The proposed model emphasizes the interrelation between modalities and supports any combination of text, audio, and video inputs, making it adaptable to a variety of realistic scenarios. Our experiments show that our approach achieves state-of-the-art performance on turn-taking and backchannel prediction tasks, achieving a 10% increase in F1-score on turn-taking and a 33% increase on backchannel prediction. Our dataset and code are publicly available online to ease of subsequent research.

Zhongnian Li, Chao Zheng, Jian Xiao et al.

This paper investigates joint channel estimation and positioning in near-field sparse extra-large multiple-input multiple-output (XL-MIMO) orthogonal frequency division multiplexing (OFDM) systems. To achieve cooperative gains between channel estimation and positioning, we propose a deep learning-based two-stage framework comprising positioning and channel estimation. In the positioning stage, the user's coordinates are predicted and utilized in the channel estimation stage, thereby enhancing the accuracy of channel estimation. Within this framework, we propose a U-shaped Mamba architecture for channel estimation and positioning, termed as CP-Mamba. This network integrates the strengths of the Mamba model with the structural advantages of U-shaped convolutional networks, enabling effective capture of local spatial features and long-range temporal dependencies of the channel. Numerical simulation results demonstrate that the proposed two-stage approach with CP-Mamba architecture outperforms existing baseline methods. Moreover, sparse arrays (SA) exhibit significantly superior performance in both channel estimation and positioning accuracy compared to conventional compact arrays.

Wangzheng Shi, Yinglin Zheng, Yuxin Lin et al.

Hair transfer is increasingly valuable across domains such as social media, gaming, advertising, and entertainment. While significant progress has been made in single-image hair transfer, video-based hair transfer remains challenging due to the need for temporal consistency, spatial fidelity, and dynamic adaptability. In this work, we propose HairShifter, a novel "Anchor Frame + Animation" framework that unifies high-quality image hair transfer with smooth and coherent video animation. At its core, HairShifter integrates a Image Hair Transfer (IHT) module for precise per-frame transformation and a Multi-Scale Gated SPADE Decoder to ensure seamless spatial blending and temporal coherence. Our method maintains hairstyle fidelity across frames while preserving non-hair regions. Extensive experiments demonstrate that HairShifter achieves state-of-the-art performance in video hairstyle transfer, combining superior visual quality, temporal consistency, and scalability. The code will be publicly available. We believe this work will open new avenues for video-based hairstyle transfer and establish a robust baseline in this field.

Yinglin Zheng, Hao Yang, Ting Zhang et al.

How to learn a universal facial representation that boosts all face analysis tasks? This paper takes one step toward this goal. In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner. On one hand, the framework involves a contrastive loss to learn high-level semantic meaning from image-text pairs. On the other hand, we propose exploring low-level information simultaneously to further enhance the face representation, by adding a masked image modeling. We perform pre-training on LAION-FACE, a dataset containing large amount of face image-text pairs, and evaluate the representation capability on multiple downstream tasks. We show that FaRL achieves better transfer performance compared with previous pre-trained models. We also verify its superiority in the low-data regime. More importantly, our model surpasses the state-of-the-art methods on face analysis tasks including face parsing and face alignment.

Chenxu Zhang, Yifan Zhao, Yifei Huang et al.

In this paper, we propose a talking face generation method that takes an audio signal as input and a short target video clip as reference, and synthesizes a photo-realistic video of the target face with natural lip motions, head poses, and eye blinks that are in-sync with the input audio signal. We note that the synthetic face attributes include not only explicit ones such as lip motions that have high correlations with speech, but also implicit ones such as head poses and eye blinks that have only weak correlation with the input audio. To model such complicated relationships among different face attributes with input audio, we propose a FACe Implicit Attribute Learning Generative Adversarial Network (FACIAL-GAN), which integrates the phonetics-aware, context-aware, and identity-aware information to synthesize the 3D face animation with realistic motions of lips, head poses, and eye blinks. Then, our Rendering-to-Video network takes the rendered face images and the attention map of eye blinks as input to generate the photo-realistic output video frames. Experimental results and user studies show our method can generate realistic talking face videos with not only synchronized lip motions, but also natural head movements and eye blinks, with better qualities than the results of state-of-the-art methods.

Yinglin Zheng, Jianmin Bao, Dong Chen et al.

Although current face manipulation techniques achieve impressive performance regarding quality and controllability, they are struggling to generate temporal coherent face videos. In this work, we explore to take full advantage of the temporal coherence for video face forgery detection. To achieve this, we propose a novel end-to-end framework, which consists of two major stages. The first stage is a fully temporal convolution network (FTCN). The key insight of FTCN is to reduce the spatial convolution kernel size to 1, while maintaining the temporal convolution kernel size unchanged. We surprisingly find this special design can benefit the model for extracting the temporal features as well as improve the generalization capability. The second stage is a Temporal Transformer network, which aims to explore the long-term temporal coherence. The proposed framework is general and flexible, which can be directly trained from scratch without any pre-training models or external datasets. Extensive experiments show that our framework outperforms existing methods and remains effective when applied to detect new sorts of face forgery videos.

Jie Xu, Yazhou Ren, Huayi Tang et al.

Multi-view clustering, a long-standing and important research problem, focuses on mining complementary information from diverse views. However, existing works often fuse multiple views' representations or handle clustering in a common feature space, which may result in their entanglement especially for visual representations. To address this issue, we present a novel VAE-based multi-view clustering framework (Multi-VAE) by learning disentangled visual representations. Concretely, we define a view-common variable and multiple view-peculiar variables in the generative model. The prior of view-common variable obeys approximately discrete Gumbel Softmax distribution, which is introduced to extract the common cluster factor of multiple views. Meanwhile, the prior of view-peculiar variable follows continuous Gaussian distribution, which is used to represent each view's peculiar visual factors. By controlling the mutual information capacity to disentangle the view-common and view-peculiar representations, continuous visual information of multiple views can be separated so that their common discrete cluster information can be effectively mined. Experimental results demonstrate that Multi-VAE enjoys the disentangled and explainable visual representations, while obtaining superior clustering performance compared with state-of-the-art methods.

Quoc-Viet Pham, Ming Zeng, Rukhsana Ruby et al.

Federated learning (FL), invented by Google in 2016, has become a hot research trend. However, enabling FL in wireless networks has to overcome the limited battery challenge of mobile users. In this regard, we propose to apply unmanned aerial vehicle (UAV)-empowered wireless power transfer to enable sustainable FL-based wireless networks. The objective is to maximize the UAV transmit power efficiency, via a joint optimization of transmission time and bandwidth allocation, power control, and the UAV placement. Directly solving the formulated problem is challenging, due to the coupling of variables. Hence, we leverage the decomposition technique and a successive convex approximation approach to develop an efficient algorithm, namely UAV for sustainable FL (UAV-SFL). Finally, simulations illustrate the potential of our proposed UAV-SFL approach in providing a sustainable solution for FL-based wireless networks, and in reducing the UAV transmit power by 32.95%, 63.18%, and 78.81% compared with the benchmarks.

Yin-Bo Liu, Ming Zeng, Qing-Hao Meng

Vision-based lane detection (LD) is a key part of autonomous driving technology, and it is also a challenging problem. As one of the important constraints of scene composition, vanishing point (VP) may provide a useful clue for lane detection. In this paper, we proposed a new multi-task fusion network architecture for high-precision lane detection. Firstly, the ERFNet was used as the backbone to extract the hierarchical features of the road image. Then, the lanes were detected using image segmentation. Finally, combining the output of lane detection and the hierarchical features extracted by the backbone, the lane VP was predicted using heatmap regression. The proposed fusion strategy was tested using the public CULane dataset. The experimental results suggest that the lane detection accuracy of our method outperforms those of state-of-the-art (SOTA) methods.

Yin-Bo Liu, Ming Zeng, Qing-Hao Meng

As an important part of linear perspective, vanishing points (VPs) provide useful clues for mapping objects from 2D photos to 3D space. Existing methods are mainly focused on extracting structural features such as lines or contours and then clustering these features to detect VPs. However, these techniques suffer from ambiguous information due to the large number of line segments and contours detected in outdoor environments. In this paper, we present a new convolutional neural network (CNN) to detect dominant VPs in natural scenes, i.e., the Dominant Vanishing Point detection Network (D-VPnet). The key component of our method is the feature line-segment proposal unit (FLPU), which can be directly utilized to predict the location of the dominant VP. Moreover, the model also uses the two main parallel lines as an assistant to determine the position of the dominant VP. The proposed method was tested using a public dataset and a Parallel Line based Vanishing Point (PLVP) dataset. The experimental results suggest that the detection accuracy of our approach outperforms those of state-of-the-art methods under various conditions in real-time, achieving rates of 115fps.

Yin-Bo Liu, Ming Zeng, Qing-Hao Meng

Unstructured road vanishing point (VP) detection is a challenging problem, especially in the field of autonomous driving. In this paper, we proposed a novel solution combining the convolutional neural network (CNN) and heatmap regression to detect unstructured road VP. The proposed algorithm firstly adopts a lightweight backbone, i.e., depthwise convolution modified HRNet, to extract hierarchical features of the unstructured road image. Then, three advanced strategies, i.e., multi-scale supervised learning, heatmap super-resolution, and coordinate regression techniques are utilized to achieve fast and high-precision unstructured road VP detection. The empirical results on Kong's dataset show that our proposed approach enjoys the highest detection accuracy compared with state-of-the-art methods under various conditions in real-time, achieving the highest speed of 33 fps.

Bitan Hou, Yujing Wang, Ming Zeng et al.

Graph is a natural representation of data for a variety of real-word applications, such as knowledge graph mining, social network analysis and biological network comparison. For these applications, graph embedding is crucial as it provides vector representations of the graph. One limitation of existing graph embedding methods is that their embedding optimization procedures are disconnected from the target application. In this paper, we propose a novel approach, namely Customized Graph Embedding (CGE) to tackle this problem. The CGE algorithm learns customized vector representations of graph nodes by differentiating the importance of distinct graph paths automatically for a specific application. Extensive experiments were carried out on a diverse set of node classification datasets, which demonstrate strong performances of CGE and provide deep insights into the model.

Jinpeng Lin, Hao Yang, Dong Chen et al.

Face parsing computes pixel-wise label maps for different semantic components (e.g., hair, mouth, eyes) from face images. Existing face parsing literature have illustrated significant advantages by focusing on individual regions of interest (RoIs) for faces and facial components. However, the traditional crop-and-resize focusing mechanism ignores all contextual area outside the RoIs, and thus is not suitable when the component area is unpredictable, e.g. hair. Inspired by the physiological vision system of human, we propose a novel RoI Tanh-warping operator that combines the central vision and the peripheral vision together. It addresses the dilemma between a limited sized RoI for focusing and an unpredictable area of surrounding context for peripheral information. To this end, we propose a novel hybrid convolutional neural network for face parsing. It uses hierarchical local based method for inner facial components and global methods for outer facial components. The whole framework is simple and principled, and can be trained end-to-end. To facilitate future research of face parsing, we also manually relabel the training data of the HELEN dataset and will make it public. Experiments on both HELEN and LFW-PL benchmarks demonstrate that our method surpasses state-of-the-art methods.

Ming Zeng, Haoxiang Gao, Tong Yu et al.

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the recurrent networks to gain insight into the models' behavior. To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention. These two mechanisms adaptively focus on important signals and sensor modalities. To further improve the understandability and mean F1 score, we add continuity constraints, considering that continuous sensor signals are more robust than discrete ones. We evaluate the approaches on three datasets and obtain state-of-the-art results. Furthermore, qualitative analysis shows that the attention learned by the models agree well with human intuition.

Ming Zeng, Tong Yu, Xiao Wang et al.

Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled examples with unlabeled examples, often resulting in improved performance. However, the semi-supervised methods studied in the activity recognition literatures assume that feature engineering is already done. In this paper, we lift this assumption and present two semi-supervised methods based on convolutional neural networks (CNNs) to learn discriminative hidden features. Our semi-supervised CNNs learn from both labeled and unlabeled data while also performing feature learning on raw sensor data. In experiments on three real world datasets, we show that our CNNs outperform supervised methods and traditional semi-supervised learning methods by up to 18% in mean F1-score (Fm).

Benjamin Elizalde, Guan-Lin Chao, Ming Zeng et al.

City-identification of videos aims to determine the likelihood of a video belonging to a set of cities. In this paper, we present an approach using only audio, thus we do not use any additional modality such as images, user-tags or geo-tags. In this manner, we show to what extent the city-location of videos correlates to their acoustic information. Success in this task suggests improvements can be made to complement the other modalities. In particular, we present a method to compute and use semantic acoustic features to perform city-identification and the features show semantic evidence of the identification. The semantic evidence is given by a taxonomy of urban sounds and expresses the potential presence of these sounds in the city- soundtracks. We used the MediaEval Placing Task set, which contains Flickr videos labeled by city. In addition, we used the UrbanSound8K set containing audio clips labeled by sound- type. Our method improved the state-of-the-art performance and provides a novel semantic approach to this task