Gengyun Jia

Yuting Xu, Jian Liang, Gengyun Jia et al.

The growing threats of deepfakes to society and cybersecurity have raised enormous public concerns, and increasing efforts have been devoted to this critical topic of deepfake video detection. Existing video methods achieve good performance but are computationally intensive. This paper introduces a simple yet effective strategy named Thumbnail Layout (TALL), which transforms a video clip into a pre-defined layout to realize the preservation of spatial and temporal dependencies. Specifically, consecutive frames are masked in a fixed position in each frame to improve generalization, then resized to sub-images and rearranged into a pre-defined layout as the thumbnail. TALL is model-agnostic and extremely simple by only modifying a few lines of code. Inspired by the success of vision transformers, we incorporate TALL into Swin Transformer, forming an efficient and effective method TALL-Swin. Extensive experiments on intra-dataset and cross-dataset validate the validity and superiority of TALL and SOTA TALL-Swin. TALL-Swin achieves 90.79$\%$ AUC on the challenging cross-dataset task, FaceForensics++ $\to$ Celeb-DF. The code is available at https://github.com/rainy-xu/TALL4Deepfake.

Xin Ma, Yaohui Wang, Gengyun Jia et al.

Diffusion models have achieved great progress in image animation due to powerful generative capabilities. However, maintaining spatio-temporal consistency with detailed information from the input static image over time (e.g., style, background, and object of the input static image) and ensuring smoothness in animated video narratives guided by textual prompts still remains challenging. In this paper, we introduce Cinemo, a novel image animation approach towards achieving better motion controllability, as well as stronger temporal consistency and smoothness. In general, we propose three effective strategies at the training and inference stages of Cinemo to accomplish our goal. At the training stage, Cinemo focuses on learning the distribution of motion residuals, rather than directly predicting subsequent via a motion diffusion model. Additionally, a structural similarity index-based strategy is proposed to enable Cinemo to have better controllability of motion intensity. At the inference stage, a noise refinement technique based on discrete cosine transformation is introduced to mitigate sudden motion changes. Such three strategies enable Cinemo to produce highly consistent, smooth, and motion-controllable results. Compared to previous methods, Cinemo offers simpler and more precise user controllability. Extensive experiments against several state-of-the-art methods, including both commercial tools and research approaches, across multiple metrics, demonstrate the effectiveness and superiority of our proposed approach.

Xin Ma, Yaohui Wang, Xinyuan Chen et al.

We propose Latte, a novel Latent Diffusion Transformer for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to the text-to-video generation (T2V) task, where Latte achieves results that are competitive with recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.

Jiayi Zou, Gengyun Jia, Bing-Kun Bao

Visual Commonsense Reasoning (VCR) refers to answering questions and providing explanations based on images. While existing methods achieve high prediction accuracy, they often overlook bias in datasets and lack debiasing strategies. In this paper, our analysis reveals co-occurrence and statistical biases in both textual and visual data. We introduce the VCR-OOD datasets, comprising VCR-OOD-QA and VCR-OOD-VA subsets, which are designed to evaluate the generalization capabilities of models across two modalities. Furthermore, we analyze the causal graphs and prediction shortcuts in VCR and adopt a backdoor adjustment method to remove bias. Specifically, we create a dictionary based on the set of correct answers to eliminate prediction shortcuts. Experiments demonstrate the effectiveness of our debiasing method across different datasets.

Xin Ma, Xiaoqiang Zhou, Huaibo Huang et al.

Most modern face completion approaches adopt an autoencoder or its variants to restore missing regions in face images. Encoders are often utilized to learn powerful representations that play an important role in meeting the challenges of sophisticated learning tasks. Specifically, various kinds of masks are often presented in face images in the wild, forming complex patterns, especially in this hard period of COVID-19. It's difficult for encoders to capture such powerful representations under this complex situation. To address this challenge, we propose a self-supervised Siamese inference network to improve the generalization and robustness of encoders. It can encode contextual semantics from full-resolution images and obtain more discriminative representations. To deal with geometric variations of face images, a dense correspondence field is integrated into the network. We further propose a multi-scale decoder with a novel dual attention fusion module (DAF), which can combine the restored and known regions in an adaptive manner. This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images. Extensive experiments clearly demonstrate that the proposed approach not only achieves more appealing results compared with state-of-the-art methods but also improves the performance of masked face recognition dramatically.

Gengyun Jia, Peipei Li, Ran He

Aesthetic quality assessment (AQA) is a challenging task due to complex aesthetic factors. Currently, it is common to conduct AQA using deep neural networks that require fixed-size inputs. Existing methods mainly transform images by resizing, cropping, and padding or employ adaptive pooling to alternately capture the aesthetic features from fixed-size inputs. However, these transformations potentially damage aesthetic features. To address this issue, we propose a simple but effective method to accomplish full-resolution image AQA by combining image padding with region of image (RoM) pooling. Padding turns inputs into the same size. RoM pooling pools image features and discards extra padded features to eliminate the side effects of padding. In addition, the image aspect ratios are encoded and fused with visual features to remedy the shape information loss of RoM pooling. Furthermore, we observe that the same image may receive different aesthetic evaluations under different themes, which we call theme criterion bias. Hence, a theme-aware model that uses theme information to guide model predictions is proposed. Finally, we design an attention-based feature fusion module to effectively utilize both the shape and theme information. Extensive experiments prove the effectiveness of the proposed method over state-of-the-art methods.