17 citations · 105 across the 20 of their papers we have counts for
11 papers · 1 filter
PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning
Yifan Lu, Ziqi Zhang, Yuxin Chen +3
The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localizat…
DSPNet: Towards Slimmable Pretrained Networks based on Discriminative Self-supervised Learning
Shaoru Wang, Zeming Li, Jin Gao +2
Self-supervised learning (SSL) has achieved promising downstream performance. However, when facing various resource budgets in real-world applications, it costs a huge computation…
SiamMask: A Framework for Fast Online Object Tracking and Segmentation
Weiming Hu, Qiang Wang, Li Zhang +2
In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method. We improve the off…
Cross-Architecture Knowledge Distillation
Yufan Liu, Jiajiong Cao, Bing Li +3
Transformer attracts much attention because of its ability to learn global relations and superior performance. In order to achieve higher performance, it is natural to distill comp…
Narrowing the Gap: Improved Detector Training with Noisy Location Annotations
Shaoru Wang, Jin Gao, Bing Li +1
Deep learning methods require massive of annotated data for optimizing parameters. For example, datasets attached with accurate bounding box annotations are essential for modern ob…
Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
Li Yang, Yan Xu, Chunfeng Yuan +3
Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They bas…
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
Yanqin Jiang, Li Zhang, Zhenwei Miao +4
3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world. Following the conventional wisdom of previous 2D object d…
A Closer Look at Self-Supervised Lightweight Vision Transformers
Shaoru Wang, Jin Gao, Zeming Li +2
Self-supervised learning on large-scale Vision Transformers (ViTs) as pre-training methods has achieved promising downstream performance. Yet, how much these pre-training paradigms…
CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation
Ziqi Zhang, Yuxin Chen, Zongyang Ma +5
Previous works of video captioning aim to objectively describe the video's actual content, which lacks subjective and attractive expression, limiting its practical application scen…
Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation
Zongyang Ma, Guan Luo, Jin Gao +5
Open-vocabulary object detection aims to detect novel object categories beyond the training set. The advanced open-vocabulary two-stage detectors employ instance-level visual-to-vi…
Learning Target-aware Representation for Visual Tracking via Informative Interactions
Mingzhe Guo, Zhipeng Zhang, Heng Fan +4
We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. Specifically, having observed that de facto frameworks perfo…