13 citations · 65 across the 19 of their papers we have counts for
20 papers
Reinforcement Learning for Large Model: A Survey
Weijia Wu, Chen Gao, Joya Chen +6
Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generat…
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
Yefei He, Luoming Zhang, Weijia Wu +3
KV cache stores key and value states from previous tokens to avoid re-computation, yet it demands substantial storage space, especially for long sequences. Adaptive KV cache compre…
Towards Accurate Post-training Quantization for Reparameterized Models
Luoming Zhang, Yefei He, Wen Fei +4
Model reparameterization is a widely accepted technique for improving inference speed without compromising performance. However, current Post-training Quantization (PTQ) methods of…
DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text
Weijia Wu, Yiming Zhang, Yefei He +4
Recently, video text detection, tracking, and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchm…
Continual Learning for Image Segmentation with Dynamic Query
Weijia Wu, Yuzhong Zhao, Zhuang Li +3
Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorpor…
Paragraph-to-Image Generation with Information-Enriched Diffusion Model
Weijia Wu, Zhuang Li, Yefei He +6
Text-to-image (T2I) models have recently experienced rapid development, achieving astonishing performance in terms of fidelity and textual alignment capabilities. However, given a…
Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM
Luoming Zhang, Wen Fei, Weijia Wu +3
Large Language Models (LLMs) pose significant hardware challenges related to memory requirements and computational ability. There are two mainstream quantization schemes for LLMs:…
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
Yefei He, Jing Liu, Weijia Wu +2
Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrai…
A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension
Weijia Wu, Yuzhong Zhao, Zhuang Li +4
Most existing cross-modal language-to-video retrieval (VR) research focuses on single-modal input from video, i.e., visual representation, while the text is omnipresent in human en…
PTQD: Accurate Post-Training Quantization for Diffusion Models
Yefei He, Luping Liu, Jing Liu +3
Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models les…
ICDAR 2023 Video Text Reading Competition for Dense and Small Text
Weijia Wu, Yuzhong Zhao, Zhuang Li +5
Recently, video text detection, tracking, and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchm…
DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
Weijia Wu, Yuzhong Zhao, Mike Zheng Shou +2
Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E,…
BiViT: Extremely Compressed Binary Vision Transformer
Yefei He, Zhenyu Lou, Luoming Zhang +4
Model binarization can significantly compress model size, reduce energy consumption, and accelerate inference through efficient bit-wise operations. Although binarizing convolution…
Binarizing by Classification: Is soft function really necessary?
Yefei He, Luoming Zhang, Weijia Wu +1
Binary neural networks leverage function to binarize weights and activations, which require gradient estimators to overcome its non-differentiability and will inevi…
Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization
Yefei He, Luoming Zhang, Weijia Wu +1
Data-free quantization is a task that compresses the neural network to low bit-width without access to original training data. Most existing data-free quantization methods cause se…
End-to-End Video Text Spotting with Transformer
Weijia Wu, Yuanqiang Cai, Chunhua Shen +4
Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post…
A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Weijia Wu, Yuanqiang Cai, Debing Zhang +5
Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World V…
Contrastive Learning of Semantic and Visual Representations for Text Tracking
Zhuang Li, Weijia Wu, Mike Zheng Shou +4
Semantic representation is of great benefit to the video text tracking(VTT) task that requires simultaneously classifying, detecting, and tracking texts in the video. Most existing…
Polygon-free: Unconstrained Scene Text Detection with Box Annotations
Weijia Wu, Enze Xie, Ruimao Zhang +3
Although a polygon is a more accurate representation than an upright bounding box for text detection, the annotations of polygons are extremely expensive and challenging. Unlike ex…
TextCohesion: Detecting Text for Arbitrary Shapes
Weijia Wu, Jici Xing, Hong Zhou
In this paper, we propose a pixel-wise method named TextCohesion for scene text detection, which splits a text instance into five key components: a Text Skeleton and four Direction…