Changqian Yu
YOU?
Author Swipe
View article: FutureNet-LOF: Joint Trajectory Prediction and Lane Occupancy Field Prediction with Future Context Encoding
FutureNet-LOF: Joint Trajectory Prediction and Lane Occupancy Field Prediction with Future Context Encoding Open
Most prior motion prediction endeavors in autonomous driving have inadequately encoded future scenarios, leading to predictions that may fail to accurately capture the diverse movements of agents (e.g., vehicles or pedestrians). To address…
View article: SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation Open
Recent real-time semantic segmentation methods usually adopt an additional semantic branch to pursue rich long-range context. However, the additional branch incurs undesirable computational overhead and slows inference speed. To eliminate …
View article: SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation Open
Recent real-time semantic segmentation methods usually adopt an additional semantic branch to pursue rich long-range context. However, the additional branch incurs undesirable computational overhead and slows inference speed. To eliminate …
View article: Semantic segmentation via pixel‐to‐center similarity calculation
Semantic segmentation via pixel‐to‐center similarity calculation Open
Since the fully convolutional network has achieved great success in semantic segmentation, lots of works have been proposed to extract discriminative pixel representations. However, the authors observe that existing methods still suffer fr…
View article: PLIP: Language-Image Pre-training for Person Representation Learning
PLIP: Language-Image Pre-training for Person Representation Learning Open
Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…
View article: Semantic Segmentation via Pixel-to-Center Similarity Calculation
Semantic Segmentation via Pixel-to-Center Similarity Calculation Open
Since the fully convolutional network has achieved great success in semantic segmentation, lots of works have been proposed focusing on extracting discriminative pixel feature representations. However, we observe that existing methods stil…
View article: GANet: Goal Area Network for Motion Forecasting
GANet: Goal Area Network for Motion Forecasting Open
Predicting the future motion of road participants is crucial for autonomous driving but is extremely challenging due to staggering motion uncertainty. Recently, most motion forecasting methods resort to the goal-based strategy, i.e., predi…
View article: CORE: Consistent Representation Learning for Face Forgery Detection
CORE: Consistent Representation Learning for Face Forgery Detection Open
Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is …
View article: Efficient Video Segmentation Models with Per-frame Inference
Efficient Video Segmentation Models with Per-frame Inference Open
Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into account,e.g…
View article: Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation Open
Image manipulation with StyleGAN has been an increasing concern in recent years.Recent works have achieved tremendous success in analyzing several semantic latent spaces to edit the attributes of the generated images.However, due to the li…
View article: Lite-HRNet: A Lightweight High-Resolution Network
Lite-HRNet: A Lightweight High-Resolution Network Open
We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular li…
View article: Representative Graph Neural Network
Representative Graph Neural Network Open
Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper, we present a Representative Graph (RepGraph) layer to dynam…
View article: BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation Open
The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable …
View article: GTNet: Generative Transfer Network for Zero-Shot Object Detection
GTNet: Generative Transfer Network for Zero-Shot Object Detection Open
We propose a Generative Transfer Network (GTNet) for zero-shot object detection (ZSD). GTNet consists of an Object Detection Module and a Knowledge Transfer Module. The Object Detection Module can learn large-scale seen domain knowledge. T…
View article: Context Prior for Scene Segmentation
Context Prior for Scene Segmentation Open
Recent works have widely explored the contextual dependencies to achieve more accurate segmentation results. However, most approaches rarely distinguish different types of contextual dependencies, which may pollute the scene understanding.…
View article: Efficient Semantic Video Segmentation with Per-frame Inference
Efficient Semantic Video Segmentation with Per-frame Inference Open
For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence, e…
View article: GTNet: Generative Transfer Network for Zero-Shot Object Detection
GTNet: Generative Transfer Network for Zero-Shot Object Detection Open
We propose a Generative Transfer Network (GTNet) for zero shot object detection (ZSD). GTNet consists of an Object Detection Module and a Knowledge Transfer Module. The Object Detection Module can learn large-scale seen domain knowledge. T…
View article: An End-to-End Network for Panoptic Segmentation
An End-to-End Network for Panoptic Segmentation Open
Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic. Traditionally, the existing approaches utilize two independent models without sharing feat…
View article: BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation Open
Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this pape…
View article: Learning a Discriminative Feature Network for Semantic Segmentation
Learning a Discriminative Feature Network for Semantic Segmentation Open
Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction. To tackle these two problems, we propose a Discriminative Feature Network (DFN), which con…