46 citations · 128 across the 23 of their papers we have counts for
22 papers · 1 filter
SteerVTE: Seamless Video Text Editing with Style and Glyph Control
Kai Zeng, Moran Li, Zhengwei Wang +6
Visual text editing aims to precisely modify text in images and videos while preserving stylistic consistency and visual realism. Despite significant advances in the image domain,…
EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
Shiqi Huang, Ziyue Wang, Zhongrong Zuo +3
Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, existing RL pipelines rely he…
TextSculptor: Training and Benchmarking Scene Text Editing
Yiheng Lin, Siyu Jiao, Xiaohan Lan +12
Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editi…
Let ViT Speak: Generative Language-Image Pre-training
Yan Fang, Mengcheng Lan, Zilong Huang +7
In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers…
AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
Yuan Zhang, Chun-Kai Fan, Sicheng Yu +6
Inspired by text prompts in large language models, visual prompts have been explored to enhance the perceptual capabilities of large vision-language models (LVLMs). However, perfor…
ZoomV: Temporal Zoom-in for Efficient Long Video Understanding
Yuan Zhang, Junwen Pan, Rui Zhang +5
Long video understanding poses a fundamental challenge for large video-language models (LVLMs) due to the overwhelming number of frames and the risk of losing essential context thr…
MammothModa: Multi-Modal Large Language Model
Qi She, Junwen Pan, Xin Wan +3
In this report, we introduce MammothModa, yet another multi-modal large language model (MLLM) designed to achieve state-of-the-art performance starting from an elementary baseline.…
PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs
Zhengyang Shen, Tao Hong, Qi She +2
Steerable models can provide very general and flexible equivariance by formulating equivariance requirements in the language of representation theory and feature fields, which has…
Background-aware Classification Activation Map for Weakly Supervised Object Localization
Lei Zhu, Qi She, Qian Chen +9
Weakly supervised object localization (WSOL) relaxes the requirement of dense annotations for object localization by using image-level classification masks to supervise its learnin…
Learning from Temporal Gradient for Semi-supervised Action Recognition
Junfei Xiao, Longlong Jing, Lin Zhang +5
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are m…
TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
Zhengwei Wang, Qi She, Aljosa Smolic
Most of existing video action recognition models ingest raw RGB frames. However, the raw video stream requires enormous storage and contains significant temporal redundancy. Video…
3rd Place Solution to Google Landmark Recognition Competition 2021
Cheng Xu, Weimin Wang, Shuai Liu +6
In this paper, we show our solution to the Google Landmark Recognition 2021 Competition. Firstly, embeddings of images are extracted via various architectures (i.e. CNN-, Transform…
MT-ORL: Multi-Task Occlusion Relationship Learning
Panhe Feng, Qi She, Lei Zhu +7
Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image. We observe two key issues in existing works: firstly, lack of a…
Inter-intra Variant Dual Representations forSelf-supervised Video Recognition
Lin Zhang, Qi She, Zhengyang Shen +1
Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models. In this paper, we find that existing contrastive learning based soluti…
Learning the Superpixel in a Non-iterative and Lifelong Manner
Lei Zhu, Qi She, Bin Zhang +4
Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent c…
Involution: Inverting the Inherence of Convolution for Visual Recognition
Duo Li, Jie Hu, Changhu Wang +5
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision. In this work, we rethink the inherent principles of standard co…
ACTION-Net: Multipath Excitation for Action Recognition
Zhengwei Wang, Qi She, Aljosa Smolic
Spatial-temporal, channel-wise, and motion patterns are three complementary and crucial types of information for video action recognition. Conventional 2D CNNs are computationally…
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions
Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez +12
In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems…
IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report
Qi She, Fan Feng, Qi Liu +33
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top finalists (out of over~…
CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition
Zhengwei Wang, Qi She, Tejo Chalasani +1
Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. A major issue in such scenarios for r…
OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning
Qi She, Fan Feng, Xinyue Hao +9
The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses u…
Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
Zhengwei Wang, Qi She, Alan F. Smeaton +2
Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. Arguably the…