ArtHDR-Net: Perceptually Realistic and Accurate HDR Content Creation

High Dynamic Range (HDR) content creation has become an important topic for modern media and entertainment sectors, gaming and Augmented/Virtual Reality industries. Many methods have been proposed to recreate the HDR counterparts of input Low Dynamic Range (LDR) images/videos given a single exposure or multi-exposure LDRs. The state-of-the-art methods focus primarily on the preservation of the reconstruction's structural similarity and the pixel-wise accuracy. However, these conventional approaches do not emphasize preserving the artistic intent of the images in terms of human visual perception, which is an essential element in media, entertainment and gaming. In this paper, we attempt to study and fill this gap. We propose an architecture called ArtHDR-Net based on a Convolutional Neural Network that uses multi-exposed LDR features as input. Experimental results show that ArtHDR-Net can achieve state-of-the-art performance in terms of the HDR-VDP-2 score (i.e., mean opinion score index) while reaching competitive performance in terms of PSNR and SSIM.

S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction

We address the video prediction task by putting forth a novel model that combines (i) our recently proposed hierarchical residual vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel spatiotemporal PixelCNN (ST-PixelCNN). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the ST-PixelCNN's ability at handling spatiotemporal information, S-HR-VQVAE can better deal with chief challenges in video prediction. These include learning spatiotemporal information, handling high dimensional data, combating blurry prediction, and implicit modeling of physical characteristics. Extensive experimental results on the KTH Human Action and Moving-MNIST tasks demonstrate that our model compares favorably against top video prediction techniques both in quantitative and qualitative evaluations despite a much smaller model size. Finally, we boost S-HR-VQVAE by proposing a novel training method to jointly estimate the HR-VQVAE and ST-PixelCNN parameters.

"Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization

Most deepfake detection methods focus on detecting spatial and/or spatio-temporal changes in facial attributes. This is because available benchmark datasets contain mostly visual-only modifications. However, a sophisticated deepfake may include small segments of audio or audio-visual manipulations that can completely change the meaning of the content. To addresses this gap, we propose and benchmark a new dataset, Localized Audio Visual DeepFake (LAV-DF), consisting of strategic content-driven audio, visual and audio-visual manipulations. The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which efficiently captures multimodal manipulations. We further improve (i.e. BA-TFD+) the baseline method by replacing the backbone with a Multiscale Vision Transformer and guide the training process with contrastive, frame classification, boundary matching and multimodal boundary matching loss functions. The quantitative analysis demonstrates the superiority of BA- TFD+ on temporal forgery localization and deepfake detection tasks using several benchmark datasets including our newly proposed dataset. The dataset, models and code are available at https://github.com/ControlNet/LAV-DF.

MARLIN: Masked Autoencoder for facial video Representation LearnINg

This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS). Our proposed framework, named MARLIN, is a facial video masked autoencoder, that learns highly robust and generic facial embeddings from abundantly available non-annotated web crawled facial videos. As a challenging auxiliary task, MARLIN reconstructs the spatio-temporal details of the face from the densely masked facial regions which mainly include eyes, nose, mouth, lips, and skin to capture local and global aspects that in turn help in encoding generic and transferable features. Through a variety of experiments on diverse downstream tasks, we demonstrate MARLIN to be an excellent facial video encoder as well as feature extractor, that performs consistently well across a variety of downstream tasks including FAR (1.13% gain over supervised benchmark), FER (2.64% gain over unsupervised benchmark), DFD (1.86% gain over unsupervised benchmark), LS (29.36% gain for Frechet Inception Distance), and even in low data regime. Our codes and pre-trained models will be made public.

Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation

We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outperform state-of-the-art generative models, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoding search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem.

Visual Representations of Physiological Signals for Fake Video Detection

Realistic fake videos are a potential tool for spreading harmful misinformation given our increasing online presence and information intake. This paper presents a multimodal learning-based method for detection of real and fake videos. The method combines information from three modalities - audio, video, and physiology. We investigate two strategies for combining the video and physiology modalities, either by augmenting the video with information from the physiology or by novelly learning the fusion of those two modalities with a proposed Graph Convolutional Network architecture. Both strategies for combining the two modalities rely on a novel method for generation of visual representations of physiological signals. The detection of real and fake videos is then based on the dissimilarity between the audio and modified video modalities. The proposed method is evaluated on two benchmark datasets and the results show significant increase in detection performance compared to previous methods.

Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization

Due to its high societal impact, deepfake detection is getting active attention in the computer vision community. Most deepfake detection methods rely on identity, facial attribute and adversarial perturbation based spatio-temporal modifications at the whole video or random locations, while keeping the meaning of the content intact. However, a sophisticated deepfake may contain only a small segment of video/audio manipulation, through which the meaning of the content can be, for example, completely inverted from sentiment perspective. To address this gap, we introduce a content driven audio-visual deepfake dataset, termed as Localized Audio Visual DeepFake (LAV-DF), explicitly designed for the task of learning temporal forgery localization. Specifically, the content driven audio-visual manipulations are performed at strategic locations in order to change the sentiment polarity of the whole video. Our baseline method for benchmarking the proposed dataset is a 3DCNN model, termed as Boundary Aware Temporal Forgery Detection (BA-TFD), which is guided via contrastive, boundary matching and frame classification loss functions. Our extensive quantitative analysis demonstrates the strong performance of the proposed method for both task of temporal forgery localization and deepfake detection.

Webcam-based Eye Gaze Tracking under Natural Head Movement

This manuscript investigates and proposes a visual gaze tracker that tackles the problem using only an ordinary web camera and no prior knowledge in any sense (scene set-up, camera intrinsic and/or extrinsic parameters). The tracker we propose is based on the observation that our desire to grant the freedom of natural head movement to the user requires 3D modeling of the scene set-up. Although, using a single low resolution web camera bounds us in dimensions (no depth can be recovered), we propose ways to cope with this drawback and model the scene in front of the user. We tackle this three-dimensional problem by realizing that it can be viewed as series of two-dimensional special cases. Then, we propose a procedure that treats each movement of the user's head as a special two-dimensional case, hence reducing the complexity of the problem back to two dimensions. Furthermore, the proposed tracker is calibration free and discards this tedious part of all previously mentioned trackers. Experimental results show that the proposed tracker achieves good results, given the restrictions on it. We can report that the tracker commits a mean error of (56.95, 70.82) pixels in x and y direction, respectively, when the user's head is as static as possible (no chin-rests are used). Furthermore, we can report that the proposed tracker commits a mean error of (87.18, 103.86) pixels in x and y direction, respectively, under natural head movement.

Self-Supervised Vision-Based Detection of the Active Speaker as a Prerequisite for Socially-Aware Language Acquisition

This paper presents a self-supervised method for detecting the active speaker in a multi-person spoken interaction scenario. We argue that this capability is a fundamental prerequisite for any artificial cognitive system attempting to acquire language in social settings. Our methods are able to detect an arbitrary number of possibly overlapping active speakers based exclusively on visual information about their face. Our methods do not rely on external annotations, thus complying with cognitive development. Instead, they use information from the auditory modality to support learning in the visual domain. The methods have been extensively evaluated on a large multi-person face-to-face interaction dataset. The results reach an accuracy of 80% on a multi-speaker setting. We believe this system represents an essential component of any artificial cognitive system or robotic platform engaging in social interaction.