Yu Tian

Yuxiao Chen, Long Zhao, Jianbo Yuan et al. · deepmind

Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at large scales is difficult. Recent studies focus on learning video-level temporal and discriminative information using contrastive learning, but overlook the hierarchical spatial-temporal nature of human skeletons. Different from such superficial supervision at the video level, we propose a self-supervised hierarchical pre-training scheme incorporated into a hierarchical Transformer-based skeleton sequence encoder (Hi-TRS), to explicitly capture spatial, short-term, and long-term temporal dependencies at frame, clip, and video levels, respectively. To evaluate the proposed self-supervised pre-training scheme with Hi-TRS, we conduct extensive experiments covering three skeleton-based downstream tasks including action recognition, action detection, and motion prediction. Under both supervised and semi-supervised evaluation protocols, our method achieves the state-of-the-art performance. Additionally, we demonstrate that the prior knowledge learned by our model in the pre-training stage has strong transfer capability for different downstream tasks.

Yuxiao Chen, Jianbo Yuan, Yu Tian et al.

Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimodal representation. FDT is a set of learnable tokens representing certain visual-semantic concepts. Both images and texts are embedded using shared FDT by first grounding multimodal inputs to FDT space and then aggregating the activated FDT representations. The matched visual and semantic concepts are enforced to be represented by the same set of discrete tokens by a sparse activation constraint. As a result, the granularity gap between the two modalities is reduced. Through both quantitative and qualitative analyses, we demonstrate that using FDT representations in CLIP-style models improves cross-modal alignment and performance in visual recognition and vision-language downstream tasks. Furthermore, we show that our method can learn more comprehensive representations, and the learned FDT capture meaningful cross-modal correspondence, ranging from objects to actions and attributes.

Shijie Geng, Jianbo Yuan, Yu Tian et al.

The success of large-scale contrastive vision-language pretraining (CLIP) has benefited both visual recognition and multimodal content understanding. The concise design brings CLIP the advantage in inference efficiency against other vision-language models with heavier cross-attention fusion layers, making it a popular choice for a wide spectrum of downstream tasks. However, CLIP does not explicitly capture the hierarchical nature of high-level and fine-grained semantics conveyed in images and texts, which is arguably critical to vision-language understanding and reasoning. To this end, we equip both the visual and language branches in CLIP with hierarchy-aware attentions, namely Hierarchy-aware CLIP (HiCLIP), to progressively discover semantic hierarchies layer-by-layer from both images and texts in an unsupervised manner. As a result, such hierarchical aggregation significantly improves the cross-modal alignment. To demonstrate the advantages of HiCLIP, we conduct qualitative analysis on its unsupervised hierarchy induction during inference, as well as extensive quantitative experiments on both visual recognition and vision-language downstream tasks.

Yu Tian, Zhangkai Ni, Baoliang Chen et al.

High-quality face images are required to guarantee the stability and reliability of automatic face recognition (FR) systems in surveillance and security scenarios. However, a massive amount of face data is usually compressed before being analyzed due to limitations on transmission or storage. The compressed images may lose the powerful identity information, resulting in the performance degradation of the FR system. Herein, we make the first attempt to study just noticeable difference (JND) for the FR system, which can be defined as the maximum distortion that the FR system cannot notice. More specifically, we establish a JND dataset including 3530 original images and 137,670 compressed images generated by advanced reference encoding/decoding software based on the Versatile Video Coding (VVC) standard (VTM-15.0). Subsequently, we develop a novel JND prediction model to directly infer JND images for the FR system. In particular, in order to maximum redundancy removal without impairment of robust identity information, we apply the encoder with multiple feature extraction and attention-based feature decomposition modules to progressively decompose face features into two uncorrelated components, i.e., identity and residual features, via self-supervised learning. Then, the residual feature is fed into the decoder to generate the residual map. Finally, the predicted JND map is obtained by subtracting the residual map from the original image. Experimental results have demonstrated that the proposed model achieves higher accuracy of JND map prediction compared with the state-of-the-art JND models, and is capable of saving more bits while maintaining the performance of the FR system compared with VTM-15.0.

Yu Tian, Yixuan Li, Baoliang Chen et al.

Assessing the quality of artificial intelligence-generated images (AIGIs) plays a crucial role in their application in real-world scenarios. However, traditional image quality assessment (IQA) algorithms primarily focus on low-level visual perception, while existing IQA works on AIGIs overemphasize the generated content itself, neglecting its effectiveness in real-world applications. To bridge this gap, we propose AIGI-VC, a quality assessment database for AI-Generated Images in Visual Communication, which studies the communicability of AIGIs in the advertising field from the perspectives of information clarity and emotional interaction. The dataset consists of 2,500 images spanning 14 advertisement topics and 8 emotion types. It provides coarse-grained human preference annotations and fine-grained preference descriptions, benchmarking the abilities of IQA methods in preference prediction, interpretation, and reasoning. We conduct an empirical study of existing representative IQA methods and large multi-modal models on the AIGI-VC dataset, uncovering their strengths and weaknesses.

Yu Tian, Zhangkai Ni, Baoliang Chen et al.

Recent years have witnessed the dramatically increased interest in face generation with generative adversarial networks (GANs). A number of successful GAN algorithms have been developed to produce vivid face images towards different application scenarios. However, little work has been dedicated to automatic quality assessment of such GAN-generated face images (GFIs), even less have been devoted to generalized and robust quality assessment of GFIs generated with unseen GAN model. Herein, we make the first attempt to study the subjective and objective quality towards generalized quality assessment of GFIs. More specifically, we establish a large-scale database consisting of GFIs from four GAN algorithms, the pseudo labels from image quality assessment (IQA) measures, as well as the human opinion scores via subjective testing. Subsequently, we develop a quality assessment model that is able to deliver accurate quality predictions for GFIs from both available and unseen GAN algorithms based on meta-learning. In particular, to learn shared knowledge from GFIs pairs that are born of limited GAN algorithms, we develop the convolutional block attention (CBA) and facial attributes-based analysis (ABA) modules, ensuring that the learned knowledge tends to be consistent with human visual perception. Extensive experiments exhibit that the proposed model achieves better performance compared with the state-of-the-art IQA models, and is capable of retaining the effectiveness when evaluating GFIs from the unseen GAN algorithms.