In today's era of digital misinformation, we are increasingly faced with new threats posed by video falsification techniques. Such falsifications range from cheapfakes (e.g., lookalikes or audio dubbing) to deepfakes (e.g., sophisticated AI media synthesis methods), which are becoming perceptually indistinguishable from real videos. To tackle this challenge, we propose a multi-modal semantic forensic approach to discover clues that go beyond detecting discrepancies in visual quality, thereby handling both simpler cheapfakes and visually persuasive deepfakes. In this work, our goal is to verify that the purported person seen in the video is indeed themselves by detecting anomalous correspondences between their facial movements and the words they are saying. We leverage the idea of attribution to learn person-specific biometric patterns that distinguish a given speaker from others. We use interpretable Action Units (AUs) to capture a persons' face and head movement as opposed to deep CNN visual features, and we are the first to use word-conditioned facial motion analysis. Unlike existing person-specific approaches, our method is also effective against attacks that focus on lip manipulation. We further demonstrate our method's effectiveness on a range of fakes not seen in training including those without video manipulation, that were not addressed in prior work.
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognition methods have achieved promising performance through the tightly coupled multi-modal spatiotemporal representation, they still suffer from (i) optimization difficulty under small data setting due to the tightly spatiotemporal-entangled modeling;(ii) information redundancy as it usually contains lots of marginal information that is weakly relevant to classification; and (iii) low interaction between multi-modal spatiotemporal information caused by insufficient late fusion. To alleviate these drawbacks, we propose to decouple and recouple spatiotemporal representation for RGB-D-based motion recognition. Specifically, we disentangle the task of learning spatiotemporal representation into 3 sub-tasks: (1) Learning high-quality and dimension independent features through a decoupled spatial and temporal modeling network. (2) Recoupling the decoupled representation to establish stronger space-time dependency. (3) Introducing a Cross-modal Adaptive Posterior Fusion (CAPF) mechanism to capture cross-modal spatiotemporal information from RGB-D data. Seamless combination of these novel designs forms a robust spatialtemporal representation and achieves better performance than state-of-the-art methods on four public motion datasets. Our code is available at https://github.com/damo-cv/MotionRGBD.
The paper aims to reveal the relationship between the performance of moving object tracking algorithms and the tracking anchors (station) deployment. The Dilution of Precision (DoP) for Time difference of arrival (TDoA) technique with respect to anchor deployment is studied. Linear estimator and non-linear estimator are used for TDoA algorithms. The research findings are: for the linear estimator, the DoP attain a lower value when other anchors are scattered around a central anchor; for the nonlinear estimator, the DoP is optimal when the anchors are scattered around the target tag. Experiments on both of the algorithms are conducted, targeting the location precision related to the anchors' deployment, with practical situations for tracking moving objects integrated with a Kalman Filter (KF) in an Ultra-Wide Band (UWB) based real-time localization system. The work provides a guideline for deploying anchors in UWB-based tracking systems.
Shortening acquisition time and reducing the motion-artifact are two of the most essential concerns in magnetic resonance imaging. As a promising solution, deep learning-based high quality MR image restoration has been investigated to generate higher resolution and motion artifact-free MR images from lower resolution images acquired with shortened acquisition time, without costing additional acquisition time or modifying the pulse sequences. However, numerous problems still exist to prevent deep learning approaches from becoming practical in the clinic environment. Specifically, most of the prior works focus solely on the network model but ignore the impact of various downsampling strategies on the acquisition time. Besides, the long inference time and high GPU consumption are also the bottle neck to deploy most of the prior works in clinics. Furthermore, prior studies employ random movement in retrospective motion artifact generation, resulting in uncontrollable severity of motion artifact. More importantly, doctors are unsure whether the generated MR images are trustworthy, making diagnosis difficult. To overcome all these problems, we employed a unified 2D deep learning neural network for both 3D MRI super resolution and motion artifact reduction, demonstrating such a framework can achieve better performance in 3D MRI restoration task compared to other states of the art methods and remains the GPU consumption and inference time significantly low, thus easier to deploy. We also analyzed several downsampling strategies based on the acceleration factor, including multiple combinations of in-plane and through-plane downsampling, and developed a controllable and quantifiable motion artifact generation method. At last, the pixel-wise uncertainty was calculated and used to estimate the accuracy of generated image, providing additional information for reliable diagnosis.
Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute descriptions shared between different classes, which act as strong priors for localizing object attributes that represent discriminative region features, enabling significant visual-semantic interaction. Although some attention-based models have attempted to learn such region features in a single image, the transferability and discriminative attribute localization of visual features are typically neglected. In this paper, we propose an attribute-guided Transformer network, termed TransZero, to refine visual features and learn attribute localization for discriminative visual embedding representations in ZSL. Specifically, TransZero takes a feature augmentation encoder to alleviate the cross-dataset bias between ImageNet and ZSL benchmarks, and improves the transferability of visual features by reducing the entangled relative geometry relationships among region features. To learn locality-augmented visual features, TransZero employs a visual-semantic decoder to localize the image regions most relevant to each attribute in a given image, under the guidance of semantic attribute information. Then, the locality-augmented visual features and semantic vectors are used to conduct effective visual-semantic interaction in a visual-semantic embedding network. Extensive experiments show that TransZero achieves the new state of the art on three ZSL benchmarks. The codes are available at: \url{https://github.com/shiming-chen/TransZero}.
Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific paradigm, leading to inefficient collaboration between tasks and high marginal costs of developing perception models for new tasks. In this paper, we present a generic perception architecture named Uni-Perceiver, which processes a variety of modalities and tasks with unified modeling and shared parameters. Specifically, Uni-Perceiver encodes different task inputs and targets from arbitrary modalities into a unified representation space with a modality-agnostic Transformer encoder and lightweight modality-specific tokenizers. Different perception tasks are modeled as the same formulation, that is, finding the maximum likelihood target for each input through the similarity of their representations. The model is pre-trained on several uni-modal and multi-modal tasks, and evaluated on a variety of downstream tasks, including novel tasks that did not appear in the pre-training stage. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks. The performance can be improved to a level close to state-of-the-art methods by conducting prompt tuning on 1% of downstream task data. Full-data fine-tuning further delivers results on par with or better than state-of-the-art results. Code shall be released.
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up approaches that try to group pixels into regions based on their visual cues or certain predefined rules. As a result, it is difficult for these bottom-up approaches to generate fine-grained semantic segmentation when coming to complicated scenes with multiple objects and some objects sharing similar visual appearance. In contrast, we propose the first top-down unsupervised semantic segmentation framework for fine-grained segmentation in extremely complicated scenarios. Specifically, we first obtain rich high-level structured semantic concept information from large-scale vision data in a self-supervised learning manner, and use such information as a prior to discover potential semantic categories presented in target datasets. Secondly, the discovered high-level semantic categories are mapped to low-level pixel features by calculating the class activate map (CAM) with respect to certain discovered semantic representation. Lastly, the obtained CAMs serve as pseudo labels to train the segmentation module and produce final semantic segmentation. Experimental results on multiple semantic segmentation benchmarks show that our top-down unsupervised segmentation is robust to both object-centric and scene-centric datasets under different semantic granularity levels, and outperforms all the current state-of-the-art bottom-up methods. Our code is available at \url{https://github.com/damo-cv/TransFGU}.
As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the final performance that is no worse than this pre-training strategy once the number of training iterations is increased in some vision tasks. In this work, we revisit this phenomenon from the perspective of generalization analysis which is popular in learning theory. Our result reveals that the final prediction precision may have a weak dependency on the pre-trained model especially in the case of large training iterations. The observation inspires us to leverage pre-training data for fine-tuning, since this data is also available for fine-tuning. The generalization result of using pre-training data shows that the final performance on a target task can be improved when the appropriate pre-training data is included in fine-tuning. With the insight of the theoretical finding, we propose a novel selection strategy to select a subset from pre-training data to help improve the generalization on the target task. Extensive experimental results for image classification tasks on 8 benchmark data sets verify the effectiveness of the proposed data selection based fine-tuning pipeline.
Transformer-based supervised pre-training achieves great performance in person re-identification (ReID). However, due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset (e.g. ImageNet-21K) to boost the performance because of the strong data fitting ability of the transformer. To address this challenge, this work targets to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure, respectively. We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks. To further reduce the domain gap and accelerate the pre-training, the Catastrophic Forgetting Score (CFS) is proposed to evaluate the gap between pre-training and fine-tuning data. Based on CFS, a subset is selected via sampling relevant data close to the down-stream ReID data and filtering irrelevant data from the pre-training dataset. For the model structure, a ReID-specific module named IBN-based convolution stem (ICS) is proposed to bridge the domain gap by learning more invariant features. Extensive experiments have been conducted to fine-tune the pre-training models under supervised learning, unsupervised domain adaptation (UDA), and unsupervised learning (USL) settings. We successfully downscale the LUPerson dataset to 50% with no performance degradation. Finally, we achieve state-of-the-art performance on Market-1501 and MSMT17. For example, our ViT-S/16 achieves 91.3%/89.9%/89.6% mAP accuracy on Market1501 for supervised/UDA/USL ReID. Codes and models will be released to https://github.com/michuanhaohao/TransReID-SSL.