A further understanding of cause and effect within observational data is critical across many domains, such as economics, health care, public policy, web mining, online advertising, and marketing campaigns. Although significant advances have been made to overcome the challenges in causal effect estimation with observational data, such as missing counterfactual outcomes and selection bias between treatment and control groups, the existing methods mainly focus on source-specific and stationary observational data. Such learning strategies assume that all observational data are already available during the training phase and from only one source. This practical concern of accessibility is ubiquitous in various academic and industrial applications. That's what it boiled down to: in the era of big data, we face new challenges in causal inference with observational data, i.e., the extensibility for incrementally available observational data, the adaptability for extra domain adaptation problem except for the imbalance between treatment and control groups, and the accessibility for an enormous amount of data. In this position paper, we formally define the problem of continual treatment effect estimation, describe its research challenges, and then present possible solutions to this problem. Moreover, we will discuss future research directions on this topic.

Face manipulation detection has been receiving a lot of attention for the reliability and security of the face images. Recent studies focus on using auxiliary information or prior knowledge to capture robust manipulation traces, which are shown to be promising. As one of the important face features, the face depth map, which has shown to be effective in other areas such as the face recognition or face detection, is unfortunately paid little attention to in literature for detecting the manipulated face images. In this paper, we explore the possibility of incorporating the face depth map as auxiliary information to tackle the problem of face manipulation detection in real world applications. To this end, we first propose a Face Depth Map Transformer (FDMT) to estimate the face depth map patch by patch from a RGB face image, which is able to capture the local depth anomaly created due to manipulation. The estimated face depth map is then considered as auxiliary information to be integrated with the backbone features using a Multi-head Depth Attention (MDA) mechanism that is newly designed. Various experiments demonstrate the advantage of our proposed method for face manipulation detection.

With the ever-growing model size and the limited availability of labeled training data, transfer learning has become an increasingly popular approach in many science and engineering domains. For classification problems, this work delves into the mystery of transfer learning through an intriguing phenomenon termed neural collapse (NC), where the last-layer features and classifiers of learned deep networks satisfy: (i) the within-class variability of the features collapses to zero, and (ii) the between-class feature means are maximally and equally separated. Through the lens of NC, our findings for transfer learning are the following: (i) when pre-training models, preventing intra-class variability collapse (to a certain extent) better preserves the intrinsic structures of the input data, so that it leads to better model transferability; (ii) when fine-tuning models on downstream tasks, obtaining features with more NC on downstream data results in better test accuracy on the given task. The above results not only demystify many widely used heuristics in model pre-training (e.g., data augmentation, projection head, self-supervised learning), but also leads to more efficient and principled fine-tuning method on downstream tasks that we demonstrate through extensive experimental results.

Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed two shortcomings: illogical synthetic SQL queries from independent column sampling and arbitrary table joins. To address these issues, we propose a novel synthesis framework that incorporates key relationships from schema, imposes strong typing, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated natural language questions. When existing powerful semantic parsers are pre-finetuned on our high-quality synthesized data, our experiments show that these models have significant accuracy boosts on popular benchmarks, including new state-of-the-art performance on Spider.

Talking face generation aims at generating photo-realistic video portraits of a target person driven by input audio. Due to its nature of one-to-many mapping from the input audio to the output video (e.g., one speech content may have multiple feasible visual appearances), learning a deterministic mapping like previous works brings ambiguity during training, and thus causes inferior visual results. Although this one-to-many mapping could be alleviated in part by a two-stage framework (i.e., an audio-to-expression model followed by a neural-rendering model), it is still insufficient since the prediction is produced without enough information (e.g., emotions, wrinkles, etc.). In this paper, we propose MemFace to complement the missing information with an implicit memory and an explicit memory that follow the sense of the two stages respectively. More specifically, the implicit memory is employed in the audio-to-expression model to capture high-level semantics in the audio-expression shared space, while the explicit memory is employed in the neural-rendering model to help synthesize pixel-level details. Our experimental results show that our proposed MemFace surpasses all the state-of-the-art results across multiple scenarios consistently and significantly.

The pretraining-finetuning paradigm has demonstrated great success in NLP and 2D image fields because of the high-quality representation ability and transferability of their pretrained models. However, pretraining such a strong model is difficult in the 3D point cloud field since the training data is limited and point cloud collection is expensive. This paper introduces \textbf{E}fficient \textbf{P}oint \textbf{C}loud \textbf{L}earning (EPCL), an effective and efficient point cloud learner for directly training high-quality point cloud models with a frozen CLIP model. Our EPCL connects the 2D and 3D modalities by semantically aligning the 2D features and point cloud features without paired 2D-3D data. Specifically, the input point cloud is divided into a sequence of tokens and directly fed into the frozen CLIP model to learn point cloud representation. Furthermore, we design a task token to narrow the gap between 2D images and 3D point clouds. Comprehensive experiments on 3D detection, semantic segmentation, classification and few-shot learning demonstrate that the 2D CLIP model can be an efficient point cloud backbone and our method achieves state-of-the-art accuracy on both real-world and synthetic downstream tasks. Code will be available.

Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation of the downsampling stage and propose the pre-abstraction group-wise window-normalization module. In particular, the window-normalization method is leveraged to unify the point densities in different parts. Furthermore, the group-wise strategy is proposed to obtain multi-type features, including texture and spatial information. We also propose the pre-abstraction module to balance local and global features. Extensive experiments show that our module performs better on several tasks. In segmentation tasks on S3DIS (Area 5), the proposed module performs better on small object recognition, and the results have more precise boundaries than others. The recognition of the sofa and the column is improved from 69.2% to 84.4% and from 42.7% to 48.7%, respectively. The benchmarks are improved from 71.7%/77.6%/91.9% (mIoU/mAcc/OA) to 72.2%/78.2%/91.4%. The accuracies of 6-fold cross-validation on S3DIS are 77.6%/85.8%/91.7%. It outperforms the best model PointNeXt-XL (74.9%/83.0%/90.3%) by 2.7% on mIoU and achieves state-of-the-art performance. The code and models are available at https://github.com/DBDXSS/Window-Normalization.git.

Video dubbing aims to translate the original speech in a film or television program into the speech in a target language, which can be achieved with a cascaded system consisting of speech recognition, machine translation and speech synthesis. To ensure the translated speech to be well aligned with the corresponding video, the length/duration of the translated speech should be as close as possible to that of the original speech, which requires strict length control. Previous works usually control the number of words or characters generated by the machine translation model to be similar to the source sentence, without considering the isochronicity of speech as the speech duration of words/characters in different languages varies. In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. Specifically, we control the speech length of generated sentence by guiding the prediction of each word with the duration information, including the speech duration of itself as well as how much duration is left for the remaining words. We design experiments on four language directions (German -> English, Spanish -> English, Chinese <-> English), and the results show that the proposed method achieves better length control ability on the generated speech than baseline methods. To make up the lack of real-world datasets, we also construct a real-world test set collected from films to provide comprehensive evaluations on the video dubbing task.

With the rapid development of cloud computing, virtual machine scheduling has become one of the most important but challenging issues for the cloud computing community, especially for practical heterogeneous request sequences. By analyzing the impact of request heterogeneity on some popular heuristic schedulers, it can be found that existing scheduling algorithms can not handle the request heterogeneity properly and efficiently. In this paper, a plug-and-play virtual machine scheduling intensifier, called Resource Assigner (ReAssigner), is proposed to enhance the scheduling efficiency of any given scheduler for heterogeneous requests. The key idea of ReAssigner is to pre-assign roles to physical resources and let resources of the same role form a virtual cluster to handle homogeneous requests. ReAssigner can cooperate with arbitrary schedulers by restricting their scheduling space to virtual clusters. With evaluations on the real dataset from Huawei Cloud, the proposed ReAssigner achieves significant scheduling performance improvement compared with some state-of-the-art scheduling methods.

One-shot segmentation of brain tissues is typically a dual-model iterative learning: a registration model (reg-model) warps a carefully-labeled atlas onto unlabeled images to initialize their pseudo masks for training a segmentation model (seg-model); the seg-model revises the pseudo masks to enhance the reg-model for a better warping in the next iteration. However, there is a key weakness in such dual-model iteration that the spatial misalignment inevitably caused by the reg-model could misguide the seg-model, which makes it converge on an inferior segmentation performance eventually. In this paper, we propose a novel image-aligned style transformation to reinforce the dual-model iterative learning for robust one-shot segmentation of brain tissues. Specifically, we first utilize the reg-model to warp the atlas onto an unlabeled image, and then employ the Fourier-based amplitude exchange with perturbation to transplant the style of the unlabeled image into the aligned atlas. This allows the subsequent seg-model to learn on the aligned and style-transferred copies of the atlas instead of unlabeled images, which naturally guarantees the correct spatial correspondence of an image-mask training pair, without sacrificing the diversity of intensity patterns carried by the unlabeled images. Furthermore, we introduce a feature-aware content consistency in addition to the image-level similarity to constrain the reg-model for a promising initialization, which avoids the collapse of image-aligned style transformation in the first iteration. Experimental results on two public datasets demonstrate 1) a competitive segmentation performance of our method compared to the fully-supervised method, and 2) a superior performance over other state-of-the-art with an increase of average Dice by up to 4.67%. The source code is available at: https://github.com/JinxLv/One-shot-segmentation-via-IST.