The explosion of user-generated videos stimulates a great demand for no-reference video quality assessment (NR-VQA). Inspired by our observation on the actions of human annotation, we put forward a Divide and Conquer Video Quality Estimator (DCVQE) for NR-VQA. Starting from extracting the frame-level quality embeddings (QE), our proposal splits the whole sequence into a number of clips and applies Transformers to learn the clip-level QE and update the frame-level QE simultaneously; another Transformer is introduced to combine the clip-level QE to generate the video-level QE. We call this hierarchical combination of Transformers as a Divide and Conquer Transformer (DCTr) layer. An accurate video quality feature extraction can be achieved by repeating the process of this DCTr layer several times. Taking the order relationship among the annotated data into account, we also propose a novel correlation loss term for model training. Experiments on various datasets confirm the effectiveness and robustness of our DCVQE model.
Audio driven talking head synthesis is a challenging task that attracts increasing attention in recent years. Although existing methods based on 2D landmarks or 3D face models can synthesize accurate lip synchronization and rhythmic head pose for arbitrary identity, they still have limitations, such as the cut feeling in the mouth mapping and the lack of skin highlights. The morphed region is blurry compared to the surrounding face. A Keypoint Based Enhancement (KPBE) method is proposed for audio driven free view talking head synthesis to improve the naturalness of the generated video. Firstly, existing methods were used as the backend to synthesize intermediate results. Then we used keypoint decomposition to extract video synthesis controlling parameters from the backend output and the source image. After that, the controlling parameters were composited to the source keypoints and the driving keypoints. A motion field based method was used to generate the final image from the keypoint representation. With keypoint representation, we overcame the cut feeling in the mouth mapping and the lack of skin highlights. Experiments show that our proposed enhancement method improved the quality of talking-head videos in terms of mean opinion score.
3D human pose and shape estimation (a.k.a. "human mesh recovery") has achieved substantial progress. Researchers mainly focus on the development of novel algorithms, while less attention has been paid to other critical factors involved. This could lead to less optimal baselines, hindering the fair and faithful evaluations of newly designed methodologies. To address this problem, this work presents the first comprehensive benchmarking study from three under-explored perspectives beyond algorithms. 1) Datasets. An analysis on 31 datasets reveals the distinct impacts of data samples: datasets featuring critical attributes (i.e. diverse poses, shapes, camera characteristics, backbone features) are more effective. Strategical selection and combination of high-quality datasets can yield a significant boost to the model performance. 2) Backbones. Experiments with 10 backbones, ranging from CNNs to transformers, show the knowledge learnt from a proximity task is readily transferable to human mesh recovery. 3) Training strategies. Proper augmentation techniques and loss designs are crucial. With the above findings, we achieve a PA-MPJPE of 47.3 mm on the 3DPW test set with a relatively simple model. More importantly, we provide strong baselines for fair comparisons of algorithms, and recommendations for building effective training configurations in the future. Codebase is available at http://github.com/smplbody/hmr-benchmarks
Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame pose and object information over a longer time span to recognize the action. Our approach achieves competitive results on two first-person hand action benchmarks, namely FPHA and H2O. Extensive ablation studies verify our design choices. We will open-source code and data to facilitate future research.
3D Multi-object tracking (MOT) ensures consistency during continuous dynamic detection, conducive to subsequent motion planning and navigation tasks in autonomous driving. However, camera-based methods suffer in the case of occlusions and it can be challenging to accurately track the irregular motion of objects for LiDAR-based methods. Some fusion methods work well but do not consider the untrustworthy issue of appearance features under occlusion. At the same time, the false detection problem also significantly affects tracking. As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection. For occlusion problems, we are the first to propose an occlusion head to select the best object appearance features multiple times effectively, reducing the influence of occlusions. To decrease the impact of false detection in tracking, we design a motion cost matrix based on confidence scores which improve the positioning and object prediction accuracy in 3D space. As existing multi-object tracking methods only consider a single category, we also propose to build a multi-category loss to implement multi-object tracking in multi-category scenes. A series of validation experiments are conducted on the KITTI and nuScenes tracking benchmarks. Our proposed method achieves state-of-the-art performance and the lowest identity switches (IDS) value (23 for Car and 137 for Pedestrian) among all multi-modal MOT methods on the KITTI test dataset. And our proposed method achieves state-of-the-art performance among all algorithms on the nuScenes test dataset with 75.3% AMOTA.
Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent motion generation methods can directly generate human motions conditioned on natural languages. However, it remains challenging to achieve diverse and fine-grained motion generation with various text inputs. To address this problem, we propose MotionDiffuse, the first diffusion model-based text-driven motion generation framework, which demonstrates several desired properties over existing methods. 1) Probabilistic Mapping. Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected. 2) Realistic Synthesis. MotionDiffuse excels at modeling complicated data distribution and generating vivid motion sequences. 3) Multi-Level Manipulation. MotionDiffuse responds to fine-grained instructions on body parts, and arbitrary-length motion synthesis with time-varied text prompts. Our experiments show MotionDiffuse outperforms existing SoTA methods by convincing margins on text-driven motion generation and action-conditioned motion generation. A qualitative analysis further demonstrates MotionDiffuse's controllability for comprehensive motion generation. Homepage: https://mingyuan-zhang.github.io/projects/MotionDiffuse.html
In dermatological disease diagnosis, the private data collected by mobile dermatology assistants exist on distributed mobile devices of patients. Federated learning (FL) can use decentralized data to train models while keeping data local. Existing FL methods assume all the data have labels. However, medical data often comes without full labels due to high labeling costs. Self-supervised learning (SSL) methods, contrastive learning (CL) and masked autoencoders (MAE), can leverage the unlabeled data to pre-train models, followed by fine-tuning with limited labels. However, combining SSL and FL has unique challenges. For example, CL requires diverse data but each device only has limited data. For MAE, while Vision Transformer (ViT) based MAE has higher accuracy over CNNs in centralized learning, MAE's performance in FL with unlabeled data has not been investigated. Besides, the ViT synchronization between the server and clients is different from traditional CNNs. Therefore, special synchronization methods need to be designed. In this work, we propose two federated self-supervised learning frameworks for dermatological disease diagnosis with limited labels. The first one features lower computation costs, suitable for mobile devices. The second one features high accuracy and fits high-performance servers. Based on CL, we proposed federated contrastive learning with feature sharing (FedCLF). Features are shared for diverse contrastive information without sharing raw data for privacy. Based on MAE, we proposed FedMAE. Knowledge split separates the global and local knowledge learned from each client. Only global knowledge is aggregated for higher generalization performance. Experiments on dermatological disease datasets show superior accuracy of the proposed frameworks over state-of-the-arts.
Amphibious ground-aerial vehicles fuse flying and driving modes to enable more flexible air-land mobility and have received growing attention recently. By analyzing the existing amphibious vehicles, we highlight the autonomous fly-driving functionality for the effective uses of amphibious vehicles in complex three-dimensional urban transportation systems. We review and summarize the key enabling technologies for intelligent flying-driving in existing amphibious vehicle designs, identify major technological barriers and propose potential solutions for future research and innovation. This paper aims to serve as a guide for research and development of intelligent amphibious vehicles for urban transportation toward the future.
This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive. Recent advanced methods proposed several lightweight transferability metrics to predict the fine-tuning results. However, these approaches only capture static representations but neglect the fine-tuning dynamics. To this end, this paper proposes a new transferability metric, called \textbf{S}elf-challenging \textbf{F}isher \textbf{D}iscriminant \textbf{A}nalysis (\textbf{SFDA}), which has many appealing benefits that existing works do not have. First, SFDA can embed the static features into a Fisher space and refine them for better separability between classes. Second, SFDA uses a self-challenging mechanism to encourage different pre-trained models to differentiate on hard examples. Third, SFDA can easily select multiple pre-trained models for the model ensemble. Extensive experiments on $33$ pre-trained models of $11$ downstream tasks show that SFDA is efficient, effective, and robust when measuring the transferability of pre-trained models. For instance, compared with the state-of-the-art method NLEEP, SFDA demonstrates an average of $59.1$\% gain while bringing $22.5$x speedup in wall-clock time. The code will be available at \url{https://github.com/TencentARC/SFDA}.
Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human annotations, we propose Mix-Teaching, an effective semi-supervised learning framework applicable to employ both labeled and unlabeled images in training stage. Mix-Teaching first generates pseudo-labels for unlabeled images by self-training. The student model is then trained on the mixed images possessing much more intensive and precise labeling by merging instance-level image patches into empty backgrounds or labeled images. This is the first to break the image-level limitation and put high-quality pseudo labels from multi frames into one image for semi-supervised training. Besides, as a result of the misalignment between confidence score and localization quality, it's hard to discriminate high-quality pseudo-labels from noisy predictions using only confidence-based criterion. To that end, we further introduce an uncertainty-based filter to help select reliable pseudo boxes for the above mixing operation. To the best of our knowledge, this is the first unified SSL framework for monocular 3D object detection. Mix-Teaching consistently improves MonoFlex and GUPNet by significant margins under various labeling ratios on KITTI dataset. For example, our method achieves around +6.34% AP@0.7 improvement against the GUPNet baseline on validation set when using only 10% labeled data. Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4.65% improvement on AP@0.7 for car detection, reaching 18.54% AP@0.7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard. The code and pretrained models will be released at https://github.com/yanglei18/Mix-Teaching.