AI with Papers - Artificial Intelligence & Deep Learning
所有人工智能都有论文。每天都有关于 #DeepLearning #MachineLearning #LLM 和 #ComputerVisionCulated 的新鲜更新，作者：Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/#AI #chatGPT
This channel is part of the discussion
AI with Papers - Artificial Intelligence & Deep Learning appears in 31 event pages on TGList🔥Ego-Exo4D Human Dataset🔥 👉Form the University of Austin, Ego-Exo4D-HM: large-scale dataset of 4D human motion reconstructions for Ego-Exo4D’s captures + reconstruction pipeline. Code, dataset, and docs 💙 👉Review 👉Paper 👉Project
🔥Unified Points n' Lines🔥 👉ETH (+Microsoft Spatial AI Lab) unveils a novel feature extractor that jointly extracts keypoints, lines, and feature descriptors within a single lightweight net. SOTA in line detection can be achieved by adding only three convolutional layers to…
🍿PanoSeg3R: SOTA 3D Segmentation🍿 👉PanoSeg3R is a novel feed-forward framework for 3D panoramic semantic segmentation. New SOTA. Code coming💙 👉Review 👉Paper 👉Project 👉Repo TBA
💄MagicMakeup Transfer💄 👉Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Authors: Zhejiang University & vivo BlueImage Lab. Repo for non commercial💙 👉Review 👉Paper harxiv.org/pdf/2607.20924 👉Project…
🌈FlowWAM: flow->action prediction🌈 👉FlowWAM is a novel dual-stream diffusion framework that adopts optical flow as a unified, video-native action representation. Repo under Apache💙 👉Review 👉Paper 👉Project 👉Repo github.com/YixiangChen515/FlowWAM
🦑Unified Segmentation n' Retrieval🦑 👉FoundYou gets an example of your object and it segments the same physical instance in a new image or retrieve it from a large gallery with ONE super-compact model. Repo/demo available💙 👉Review 👉Paper arxiv.org/pdf/2608.29917 👉Project…