StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing

Given a script, the challenge in Movie Dubbing (Visual Voice Cloning, V2C) is to generate speech that aligns well with the video in both time and emotion, based on the tone of a reference audio track. Existing state-of-the-art V2C models break the phonemes in the script according to the divisions between video frames, which solves the temporal alignment problem but leads to incomplete phoneme pronunciation and poor identity stability. To address this problem, we propose StyleDubber, which switches dubbing learning from the frame level to phoneme level. It contains three main components: (1) A multimodal style adaptor operating at the phoneme level to learn pronunciation style from the reference audio, and generate intermediate representations informed by the facial emotion presented in the video; (2) An utterance-level style learning module, which guides both the mel-spectrogram decoding and the refining processes from the intermediate embeddings to improve the overall style expression; And (3) a phoneme-guided lip aligner to maintain lip sync. Extensive experiments on two of the primary benchmarks, V2C and Grid, demonstrate the favorable performance of the proposed method as compared to the current state-of-the-art. The source code and trained models will be released to the public.

Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization

Diffusion-based text-to-image personalization have achieved great success in generating subjects specified by users among various contexts. Even though, existing finetuning-based methods still suffer from model overfitting, which greatly harms the generative diversity, especially when given subject images are few. To this end, we propose Pick-and-Draw, a training-free semantic guidance approach to boost identity consistency and generative diversity for personalization methods. Our approach consists of two components: appearance picking guidance and layout drawing guidance. As for the former, we construct an appearance palette with visual features from the reference image, where we pick local patterns for generating the specified subject with consistent identity. As for layout drawing, we outline the subject's contour by referring to a generative template from the vanilla diffusion model, and inherit the strong image prior to synthesize diverse contexts according to different text conditions. The proposed approach can be applied to any personalized diffusion models and requires as few as a single reference image. Qualitative and quantitative experiments show that Pick-and-Draw consistently improves identity consistency and generative diversity, pushing the trade-off between subject fidelity and image-text fidelity to a new Pareto frontier.

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video

Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is caused by the uneven temporal distribution of the target moments for samples with similar semantic components in input videos or query texts. Existing methods resort to utilizing prior knowledge about bias to artificially break this uneven distribution, which only removes a limited amount of significant language biases. In this work, we propose the bias-conflict sample synthesis and adversarial removal debias strategy (BSSARD), which dynamically generates bias-conflict samples by explicitly leveraging potentially spurious correlations between single-modality features and the temporal position of the target moments. Through adversarial training, its bias generators continuously introduce biases and generate bias-conflict samples to deceive its grounding model. Meanwhile, the grounding model continuously eliminates the introduced biases, which requires it to model multi-modality alignment information. BSSARD will cover most kinds of coupling relationships and disrupt language and visual biases simultaneously. Extensive experiments on Charades-CD and ActivityNet-CD demonstrate the promising debiasing capability of BSSARD. Source codes are available at https://github.com/qzhb/BSSARD.

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection

Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the \textit{Anomaly Overfitting} and \textit{Homophily Trap} problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate \textit{Anomaly Overfitting}. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets.

Subject-Oriented Video Captioning

Describing video content according to users' needs is a long-held goal. Although existing video captioning methods have made significant progress, the generated captions may not focus on the entity that users are particularly interested in. To address this problem, we propose a new video captioning task, subject-oriented video captioning, which allows users to specify the describing target via a bounding box. To support this task, we construct two subject-oriented video captioning datasets based on two widely used video captioning datasets: MSVD and MSRVTT, by annotating subjects in each video for each caption. These datasets pave the way for future technique development. As the first attempt, we evaluate four state-of-the-art general video captioning models, and have observed a large performance drop. We then explore several strategies to enable them to describe the desired target. Experimental results show obvious improvement, but there is still a large room for further exploration in this field.

Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting

Video Individual Counting (VIC) aims to predict the number of unique individuals in a single video. % Existing methods learn representations based on trajectory labels for individuals, which are annotation-expensive. % To provide a more realistic reflection of the underlying practical challenge, we introduce a weakly supervised VIC task, wherein trajectory labels are not provided. Instead, two types of labels are provided to indicate traffic entering the field of view (inflow) and leaving the field view (outflow). % We also propose the first solution as a baseline that formulates the task as a weakly supervised contrastive learning problem under group-level matching. In doing so, we devise an end-to-end trainable soft contrastive loss to drive the network to distinguish inflow, outflow, and the remaining. % To facilitate future study in this direction, we generate annotations from the existing VIC datasets SenseCrowd and CroHD and also build a new dataset, UAVVIC. % Extensive results show that our baseline weakly supervised method outperforms supervised methods, and thus, little information is lost in the transition to the more practically relevant weakly supervised task. The code and trained model will be public at \href{https://github.com/streamer-AP/CGNet}{CGNet}

Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection

The goal of weakly supervised video anomaly detection is to learn a detection model using only video-level labeled data. However, prior studies typically divide videos into fixed-length segments without considering the complexity or duration of anomalies. Moreover, these studies usually just detect the most abnormal segments, potentially overlooking the completeness of anomalies. To address these limitations, we propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection, which learns multi-scale temporal features. Specifically, to handle duration variations of abnormal events, we first propose a multi-scale temporal modeling module, capable of extracting features from segments of varying lengths and capturing both local and global visual information across different temporal scales. Then, we design a dynamic erasing strategy, which dynamically assesses the completeness of the detected anomalies and erases prominent abnormal segments in order to encourage the model to discover gentle abnormal segments in a video. The proposed method obtains favorable performance compared to several state-of-the-art approaches on three datasets: XD-Violence, TAD, and UCF-Crime. Code will be made available at https://github.com/ArielZc/DE-Net.

DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework

The Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed classification scenarios. Nevertheless, most existing methods primarily assume that training and testing examples are drawn i.i.d. from the same distribution, which is often unachievable in practice. Distributionally Robust Optimization (DRO) enhances model performance by optimizing it for the local worst-case scenario, but directly integrating AUC optimization with DRO results in an intractable optimization problem. To tackle this challenge, methodically we propose an instance-wise surrogate loss of Distributionally Robust AUC (DRAUC) and build our optimization framework on top of it. Moreover, we highlight that conventional DRAUC may induce label bias, hence introducing distribution-aware DRAUC as a more suitable metric for robust AUC learning. Theoretically, we affirm that the generalization gap between the training loss and testing error diminishes if the training set is sufficiently large. Empirically, experiments on corrupted benchmark datasets demonstrate the effectiveness of our proposed method. Code is available at: https://github.com/EldercatSAM/DRAUC.

Modeling the Uncertainty with Maximum Discrepant Students for Semi-supervised 2D Pose Estimation

Semi-supervised pose estimation is a practically challenging task for computer vision. Although numerous excellent semi-supervised classification methods have emerged, these methods typically use confidence to evaluate the quality of pseudo-labels, which is difficult to achieve in pose estimation tasks. For example, in pose estimation, confidence represents only the possibility that a position of the heatmap is a keypoint, not the quality of that prediction. In this paper, we propose a simple yet efficient framework to estimate the quality of pseudo-labels in semi-supervised pose estimation tasks from the perspective of modeling the uncertainty of the pseudo-labels. Concretely, under the dual mean-teacher framework, we construct the two maximum discrepant students (MDSs) to effectively push two teachers to generate different decision boundaries for the same sample. Moreover, we create multiple uncertainties to assess the quality of the pseudo-labels. Experimental results demonstrate that our method improves the performance of semi-supervised pose estimation on three datasets.

Generating Unbiased Pseudo-labels via a Theoretically Guaranteed Chebyshev Constraint to Unify Semi-supervised Classification and Regression

Both semi-supervised classification and regression are practically challenging tasks for computer vision. However, semi-supervised classification methods are barely applied to regression tasks. Because the threshold-to-pseudo label process (T2L) in classification uses confidence to determine the quality of label. It is successful for classification tasks but inefficient for regression tasks. In nature, regression also requires unbiased methods to generate high-quality labels. On the other hand, T2L for classification often fails if the confidence is generated by a biased method. To address this issue, in this paper, we propose a theoretically guaranteed constraint for generating unbiased labels based on Chebyshev's inequality, combining multiple predictions to generate superior quality labels from several inferior ones. In terms of high-quality labels, the unbiased method naturally avoids the drawback of T2L. Specially, we propose an Unbiased Pseudo-labels network (UBPL network) with multiple branches to combine multiple predictions as pseudo-labels, where a Feature Decorrelation loss (FD loss) is proposed based on Chebyshev constraint. In principle, our method can be used for both classification and regression and can be easily extended to any semi-supervised framework, e.g. Mean Teacher, FixMatch, DualPose. Our approach achieves superior performance over SOTAs on the pose estimation datasets Mouse, FLIC and LSP, as well as the classification datasets CIFAR10/100 and SVHN.