Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks66 from public data
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation749
This work proposes an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously, and can achieve state-of-the-art temporal action detection performance.
- Deep Metric Learning with Angular Loss549
This paper proposes a novel angular loss, which takes angle relationship into account, for learning better similarity metric, and aims at constraining the angle at the negative point of triplet triangles.
- 384
- Image Inpainting With Learnable Bidirectional Attention Maps282
This paper presents a learnable attention map module for learning feature re-normalization and mask-updating in an end-to-end manner, which is effective in adapting to irregular holes and propagation of convolution layers.
- Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification233
It is shown that temporal information, especially longer-term patterns, may not be necessary to achieve competitive results on common trimmed video classification datasets, and a local feature integration framework based on attention clusters is proposed, which achieves competitive results across all of these datasets.
- Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification232
This work proposes an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships, and generates novel cross-modality attention maps which outperforms other existing state-of-the-arts methods for multi-label classification.
- 223
- Dynamic Instance Normalization for Arbitrary Style Transfer222
The proposed Dynamic Instance Normalization (DIN) provides flexible support for state-of-the-art convolutional operations, and thus triggers novel functionalities, such as uniform-stroke placement for non-natural images and automatic spatial-stroke control.
- Perspective-Guided Convolution Networks for Crowd Counting217
A novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i.e. PGCNet) is proposed, which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect.
- Multi-Label Classification with Label Graph Superimposing206
A label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recognition in the following two aspects and to leverage embedding of the whole label system for better representation learning.
- Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos173
A reinforcement learning based framework improved by multi-task learning is proposed which achieves state-of-the-art performance on ActivityNet'18 DenseCaption dataset and Charades-STA dataset while observing only 10 or less clips per video.
- FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation156
FreeSeg is proposed, a generic framework to accomplish Unified, Universal and Open-Vocabulary Image Segmentation, which optimizes an all-in-one network via one-shot training and employs the same architecture and parameters to handle diverse segmentation tasks seamlessly in the inference procedure.
- Multimodal Keyless Attention Fusion for Video Classification147
This work proposes Keyless Attention as an elegant and efficient means to more effectively account for the sequential nature of the data and finds that Multimodal Keyless attention Fusion is the most successful at discerning interactions between modalities.
- StNet: Local and Global Spatial-Temporal Modeling for Action Recognition146
A novel spatial temporal network (StNet) architecture for both local and global spatial-temporal modeling in videos that outperforms several state-of-the-art approaches in action recognition and can strike a satisfying trade-off between recognition accuracy and model complexity is explored.
- RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning143
It is observed that the relative playback speed is more consistent with motion patterns and thus provides more effective and stable supervision for representation learning, and a new way to perceive the playback speed and exploit the relative speed between two video clips as labels is proposed.
- Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition139
This work focuses on improving untrimmed video classification via developing a learning-based frame sampling strategy and proposes to solve the problems with multi-agent reinforcement learning (MARL), a novel RNN-based context-aware observation network which jointly models context information among nearby agents.
- Dynamic Computational Time for Visual Attention130
A dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM) by adding an additional continue/stop action per time step to RAM and using reinforcement learning to learn both the optimal attention policy and stopping policy.
- 126
- 123
- Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement116
A two-stage graph-based and model-agnostic framework, called Graph-PCNN, with a localization subnet and a graph pose refinement module added onto the original heatmap regression network to get more accurate localization results.
- Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection104
A domain adaptation like approach is innovatively proposed to enhance the robustness of the feature representation in 3D object detection and mimics the functionality of the human brain when proceeding object perception.
- Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition91
An attribute-guided attention localization scheme where the local region localizers are learned under the guidance of part attribute descriptions is introduced, which is more amenable than the accurate part location annotation required by traditional part-based fine-grained recognition methods.
- Segment as Points for Efficient Online Multi-Object Tracking and Segmentation85
This paper proposes a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation and builds a more challenging MOTS dataset named APOLLO MOTS with higher instance density.
- ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection78
A novel framework named ZoomNet for stereo imagery-based 3D detection, which surpasses all previous state-of-the-art methods by large margins and introduces to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the3D detection quality.
- 68
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.