However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.
In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space.
To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net).
Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.
Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label.
In autonomous driving, LiDAR point-clouds and RGB images are two major data modalities with complementary cues for 3D object detection.
The network is mainly composed of two components: a context-aware local retouching layer (LRL) and an adaptive blend pyramid layer (BPL).
Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available.
This paper proposes a novel approach to object detection on drone imagery, namely Multi-Proxy Detection Network with Unified Foreground Packing (UFPMP-Det).
The proposed model consists of a 3D face reconstruction module, a face segmentation module, and an image generation module.
The recent studies on semantic segmentation are starting to notice the significance of the boundary information, where most approaches see boundaries as the supplement of semantic details.
Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation of network representation and dramatically accelerates Neural Architecture Search (NAS) by almost thousands of times in GPU-day.
This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way.
Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors.
The widespread adoption of online social networks in daily life has created a pressing need for effectively classifying user-generated content.
Missing textures in the incomplete UV map are further full-filled by the UV generator.
The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image style properly, which refers to the color, brightness, saturation, etc.
In this paper, an effective pipeline to automatic 4D Facial Expression Recognition (4D FER) is proposed.
Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies.
Ranked #20 on Anomaly Detection on MVTec AD (using extra training data)
Objects in aerial images usually have arbitrary orientations and are densely located over the ground, making them extremely challenge to be detected.
LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects.
Ranked #4 on 3D Object Detection on KITTI Cars Easy val
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited.
Ranked #10 on Few-Shot Object Detection on MS-COCO (30-shot)
They fail to improve object detectors in their vanilla forms due to the domain gap between the Web images and curated datasets.
Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred.
In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general convolutions.
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.
Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled.
Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection.
Ranked #119 on Object Detection on COCO test-dev
Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting.
Ranked #9 on Image Classification on WebVision-1000
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers.
We show that machine learning can be leveraged to assist the automation engineer in classifying automation, finding similar code snippets, and reasoning about the hardware selection of sensors and actuators.
In this work, we introduce the problem of graph representation ensemble learning and provide a first of its kind framework to aggregate multiple graph embedding methods efficiently.
We use the comparisons on our 100 benchmark graphs to define GFS-score, that can be applied to any embedding method to quantify its performance.
Convolutional Neural Network (CNN) based Deep Learning (DL) has achieved great progress in many real-life applications.
The two underlying requirements of face age progression, i. e. aging accuracy and identity permanence, are not well studied in the literature.
In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply representing the gait process by averaging silhouette images.
Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs.
In order to accurately detect defects in patterned fabric images, a novel detection algorithm based on Gabor-HOG (GHOG) and low-rank decomposition is proposed in this paper.
Face aging simulation has received rising investigations nowadays, whereas it still remains a challenge to generate convincing and natural age-progressed face images.