paper-with-me

Papers

InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language

2023-05-09 · Zhaoyang Liu, Yinan He, Wenhai Wang, Weiyun Wang, Yi Wang, Shoufa Chen, Qinglong Zhang, Zeqiang Lai, Yang Yang, Qingyun Li, Jiashuo Yu, Kunchang Li, Zhe Chen, Xue Yang, Xizhou Zhu, Yali Wang, LiMin Wang, Ping Luo, Jifeng Dai, Yu Qiao

We present an interactive visual framework named InternGPT, or iGPT for short. The framework integrates chatbots that have planning and reasoning capabilities, such as ChatGPT, with non-verbal instructions like pointing movements that enable users to directly manipulate images or videos on the screen. Pointing (including gestures, cursors, etc.) movements can provide more flexibility and precision in performing vision-centric tasks that require fine-grained control, editing, and generation of visual content. The name InternGPT stands for \textbf{inter}action, \textbf{n}onverbal, and \textbf{chat}bots. Different from existing interactive systems that rely on pure language, by incorporating pointing instructions, the proposed iGPT significantly improves the efficiency of communication between users and chatbots, as well as the accuracy of chatbots in vision-centric tasks, especially in complicated visual scenarios where the number of objects is greater than 2. Additionally, in iGPT, an auxiliary control mechanism is used to improve the control capability of LLM, and a large vision-language model termed Husky is fine-tuned for high-quality multi-modal dialogue (impressing ChatGPT-3.5-turbo with 93.89\% GPT-4 Quality). We hope this work can spark new ideas and directions for future interactive visual systems. Welcome to watch the code at https://github.com/OpenGVLab/InternGPT.

📄 PDF Abstract BibTeX arXiv:2305.05662

Code (2)

opengvlab/internchat 공식 구현 pytorch
opengvlab/interngpt 공식 구현 pytorch

Tasks

Language Modelling

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

2023-05-18 · NeurIPS 2023 11 · Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu 외

Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with immense potential across …

DecoderLanguage ModelingLanguage ModellingLarge Language Model

Interaction-Centric Knowledge Infusion and Transfer for Open-Vocabulary Scene Graph Generation

2025-11-08 · Lin Li, Chuhan Zhang, Dong Zhang, Chong Sun 외 arxiv

Open-vocabulary scene graph generation (OVSGG) extends traditional SGG by recognizing novel objects and relationships beyond predefined categories, leveraging the knowledge from pre-trained large-scale models. Existing O…

Scene Graph GenerationKnowledge DistillationGeneral Knowledge

Recognizing Micro-Actions and Reactions From Paired Egocentric Videos

2016-06-01 · CVPR 2016 6 · Ryo Yonetani, Kris M. Kitani, Yoichi Sato

We aim to understand the dynamics of social interactions between two people by recognizing their actions and reactions using a head-mounted camera. Our work will impact several first-person vision tasks that need the det…

Video Summarization

The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain

2020-10-12 · Francesco Ragusa, Antonino Furnari, Salvatore Livatino, Giovanni Maria Farinella

Wearable cameras allow to collect images and videos of humans interacting with the world. While human-object interactions have been thoroughly investigated in third person vision, the problem has been understudied in ego…

Action RecognitionActive Object DetectionHuman-Object Interaction DetectionObject+3

Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision

2022-01-20 · CVPR 2022 1 · Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar 외

Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can onl…

3D Human Pose EstimationEgocentric Pose EstimationPose Estimation