We propose a sparse and privacy-enhanced representation for Human Pose Estimation (HPE). Given a perspective camera, we use a proprietary motion vector sensor(MVS) to extract an edge image and a two-directional motion vector image at each time frame. Both edge and motion vector images are sparse and contain much less information (i.e., enhancing human privacy). We advocate that edge information is essential for HPE, and motion vectors complement edge information during fast movements. We propose a fusion network leveraging recent advances in sparse convolution used typically for 3D voxels to efficiently process our proposed sparse representation, which achieves about 13x speed-up and 96% reduction in FLOPs. We collect an in-house edge and motion vector dataset with 16 types of actions by 40 users using the proprietary MVS. Our method outperforms individual modalities using only edge or motion vector images. Finally, we validate the privacy-enhanced quality of our sparse representation through face recognition on CelebA (a large face dataset) and a user study on our in-house dataset.
The volume and diversity of training data are critical for modern deep learningbased methods. Compared to the massive amount of labeled perspective images, 360 panoramic images fall short in both volume and diversity. In this paper, we propose PanoMixSwap, a novel data augmentation technique specifically designed for indoor panoramic images. PanoMixSwap explicitly mixes various background styles, foreground furniture, and room layouts from the existing indoor panorama datasets and generates a diverse set of new panoramic images to enrich the datasets. We first decompose each panoramic image into its constituent parts: background style, foreground furniture, and room layout. Then, we generate an augmented image by mixing these three parts from three different images, such as the foreground furniture from one image, the background style from another image, and the room structure from the third image. Our method yields high diversity since there is a cubical increase in image combinations. We also evaluate the effectiveness of PanoMixSwap on two indoor scene understanding tasks: semantic segmentation and layout estimation. Our experiments demonstrate that state-of-the-art methods trained with PanoMixSwap outperform their original setting on both tasks consistently.
We propose ImGeoNet, a multi-view image-based 3D object detection framework that models a 3D space by an image-induced geometry-aware voxel representation. Unlike previous methods which aggregate 2D features into 3D voxels without considering geometry, ImGeoNet learns to induce geometry from multi-view images to alleviate the confusion arising from voxels of free space, and during the inference phase, only images from multiple views are required. Besides, a powerful pre-trained 2D feature extractor can be leveraged by our representation, leading to a more robust performance. To evaluate the effectiveness of ImGeoNet, we conduct quantitative and qualitative experiments on three indoor datasets, namely ARKitScenes, ScanNetV2, and ScanNet200. The results demonstrate that ImGeoNet outperforms the current state-of-the-art multi-view image-based method, ImVoxelNet, on all three datasets in terms of detection accuracy. In addition, ImGeoNet shows great data efficiency by achieving results comparable to ImVoxelNet with 100 views while utilizing only 40 views. Furthermore, our studies indicate that our proposed image-induced geometry-aware representation can enable image-based methods to attain superior detection accuracy than the seminal point cloud-based method, VoteNet, in two practical scenarios: (1) scenarios where point clouds are sparse and noisy, such as in ARKitScenes, and (2) scenarios involve diverse object classes, particularly classes of small objects, as in the case in ScanNet200.
Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data. However, while applying CLIP to a downstream target domain, the presence of visual and text domain gaps and cross-modality misalignment can greatly impact the model performance. To address such challenges, we propose ReCLIP, the first source-free domain adaptation method for vision-language models, which does not require any source data or target labeled data. ReCLIP first learns a projection space to mitigate the misaligned visual-text embeddings and learns pseudo labels, and then deploys cross-modality self-training with the pseudo labels, to update visual and text encoders, refine labels and reduce domain gaps and misalignments iteratively. With extensive experiments, we demonstrate ReCLIP reduces the average error rate of CLIP from 30.17% to 25.06% on 22 image classification benchmarks.
Airborne particles are the medium for SARS-CoV-2 to invade the human body. Light also reflects through suspended particles in the air, allowing people to see a colorful world. Impressionism is the most prominent art school that explores the spectrum of color created through color reflection of light. We find similarities of color structure and color stacking in the Impressionist paintings and the illustrations of the novel coronavirus by artists around the world. With computerized data analysis through the main tones, the way of color layout, and the way of color stacking in the paintings of the Impressionists, we train computers to draw the novel coronavirus in an Impressionist style using a Generative Adversarial Network to create our artwork "Medium. Permeation". This artwork is composed of 196 randomly generated viral pictures arranged in a 14 by 14 matrix to form a large-scale painting. In addition, we have developed an extended work: Gradual Change, which is presented as video art. We use Graph Neural Network to present 196 paintings of the new coronavirus to the audience one by one in a gradual manner. In front of LED TV screen, audience will find 196 virus paintings whose colors will change continuously. This large video painting symbolizes that worldwide 196 countries have been invaded by the epidemic, and every nation continuously pops up mutant viruses. The speed of vaccine development cannot keep up with the speed of virus mutation. This is also the first generative art in the world based on the common features and a metaphorical symbiosis between Impressionist art and the novel coronavirus. This work warns us of the unprecedented challenges posed by the SARS-CoV-2, implying that the world should not ignore the invisible enemy who uses air as a medium.
In modern fulfillment warehouses, agents traverse the map to complete endless tasks that arrive on the fly, which is formulated as a lifelong Multi-Agent Path Finding (lifelong MAPF) problem. The goal of tackling this challenging problem is to find the path for each agent in a finite runtime while maximizing the throughput. However, existing methods encounter exponential growth of runtime and undesirable phenomena of deadlocks and rerouting as the map size or agent density grows. To address these challenges in lifelong MAPF, we explore the idea of highways mainly studied for one-shot MAPF (i.e., finding paths at once beforehand), which reduces the complexity of the problem by encouraging agents to move in the same direction. We utilize two methods to incorporate the highway idea into the lifelong MAPF framework and discuss the properties that minimize the existing problems of deadlocks and rerouting. The experimental results demonstrate that the runtime is considerably reduced and the decay of throughput is gradually insignificant as the map size enlarges under the settings of the highway. Furthermore, when the density of agents increases, the phenomena of deadlocks and rerouting are significantly reduced by leveraging the highway.
We propose a content-based system for matching video and background music. The system aims to address the challenges in music recommendation for new users or new music give short-form videos. To this end, we propose a cross-modal framework VMCML that finds a shared embedding space between video and music representations. To ensure the embedding space can be effectively shared by both representations, we leverage CosFace loss based on margin-based cosine similarity loss. Furthermore, we establish a large-scale dataset called MSVD, in which we provide 390 individual music and the corresponding matched 150,000 videos. We conduct extensive experiments on Youtube-8M and our MSVD datasets. Our quantitative and qualitative results demonstrate the effectiveness of our proposed framework and achieve state-of-the-art video and music matching performance.
To track the 3D locations and trajectories of the other traffic participants at any given time, modern autonomous vehicles are equipped with multiple cameras that cover the vehicle's full surroundings. Yet, camera-based 3D object tracking methods prioritize optimizing the single-camera setup and resort to post-hoc fusion in a multi-camera setup. In this paper, we propose a method for panoramic 3D object tracking, called CC-3DT, that associates and models object trajectories both temporally and across views, and improves the overall tracking consistency. In particular, our method fuses 3D detections from multiple cameras before association, reducing identity switches significantly and improving motion modeling. Our experiments on large-scale driving datasets show that fusion before association leads to a large margin of improvement over post-hoc fusion. We set a new state-of-the-art with 12.6% improvement in average multi-object tracking accuracy (AMOTA) among all camera-based methods on the competitive NuScenes 3D tracking benchmark, outperforming previously published methods by 6.5% in AMOTA with the same 3D detector.
Semiconductor manufacturing is on the cusp of a revolution: the Internet of Things (IoT). With IoT we can connect all the equipment and feed information back to the factory so that quality issues can be detected. In this situation, more and more edge devices are used in wafer inspection equipment. This edge device must have the ability to quickly detect defects. Therefore, how to develop a high-efficiency architecture for automatic defect classification to be suitable for edge devices is the primary task. In this paper, we present a novel architecture that can perform defect classification in a more efficient way. The first function is self-proliferation, using a series of linear transformations to generate more feature maps at a cheaper cost. The second function is self-attention, capturing the long-range dependencies of feature map by the channel-wise and spatial-wise attention mechanism. We named this method as self-proliferation-and-attention neural network. This method has been successfully applied to various defect pattern classification tasks. Compared with other latest methods, SP&A-Net has higher accuracy and lower computation cost in many defect inspection tasks.
Although significant progress has been made in face recognition, demographic bias still exists in face recognition systems. For instance, it usually happens that the face recognition performance for a certain demographic group is lower than the others. In this paper, we propose MixFairFace framework to improve the fairness in face recognition models. First of all, we argue that the commonly used attribute-based fairness metric is not appropriate for face recognition. A face recognition system can only be considered fair while every person has a close performance. Hence, we propose a new evaluation protocol to fairly evaluate the fairness performance of different approaches. Different from previous approaches that require sensitive attribute labels such as race and gender for reducing the demographic bias, we aim at addressing the identity bias in face representation, i.e., the performance inconsistency between different identities, without the need for sensitive attribute labels. To this end, we propose MixFair Adapter to determine and reduce the identity bias of training samples. Our extensive experiments demonstrate that our MixFairFace approach achieves state-of-the-art fairness performance on all benchmark datasets.