AI with Papers - Artificial Intelligence & Deep Learning
前往频道在 Telegram
All the AI with papers. Every day fresh updates about #DeepLearning #MachineLearning #LLM & #ComputerVision Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/ #AI #chatGPT
显示更多📈 Telegram 频道 AI with Papers - Artificial Intelligence & Deep Learning 的分析概览
频道 AI with Papers - Artificial Intelligence & Deep Learning (@ai_deeplearning) 英语 语言赛道中的 是活跃参与者。目前社区聚集了 17 260 名订阅者，在 技术与应用 类别中位列第 7 543，并在 马来西亚 地区排名第 2 150 位。
📊 受众指标与增长动态
自 невідомо 创建以来，项目保持高速增长，吸引了 17 260 名订阅者。
根据 28 十月, 2026 的最新数据，频道保持稳定运转。过去 30 天订阅人数变化为 229，过去 24 小时变化为 1，整体触达仍然可观。
- 认证状态： 未认证
- 互动率 (ER)： 平均受众互动率为 17.18%。内容发布后 24 小时内通常能获得 7.02% 的反应，占订阅者总量。
- 帖子覆盖： 每篇帖子平均可获得 2 965 次浏览，首日通常累积 1 211 次浏览。
- 互动与反馈： 受众积极参与，单帖平均反应数为 15。
- 主题关注点： 内容集中在 framework, object, dataset, tba, depth 等核心主题上。
📝 描述与内容策略
作者将该频道定位为表达主观观点的平台：
“All the AI with papers. Every day fresh updates about #DeepLearning #MachineLearning #LLM & #ComputerVision
Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/
#AI #chatGPT”
凭借高频更新（最新数据采集于 29 十月, 2026），频道始终保持新鲜度与高覆盖。分析显示受众积极互动，使其成为 技术与应用 类别中的关键影响点。
17 260
订阅者
+124 小时
+17 天
+22930 天
帖子存档
🟧 PlanT: Driving Plan w/ Transformer 🟧
👉PlanT: planning via transformer. Imitation learning with compact object-level representation
😎Review https://bit.ly/3Ni2MxN
😎Project www.katrinrenz.de/plant/
😎Paper arxiv.org/pdf/2210.14222.pdf
😎Code github.com/autonomousvision/plant
🌨️Multi NeRF-supervised Depth-Pose🌨️
👉NeRF-supervised disentanglement of depth/camera pose from large-scale clips
😎Review https://bit.ly/3gS4Z7e
😎Paper arxiv.org/pdf/2210.07181.pdf
😎Project oasisyang.github.io/self-mpinerf
🎸MUSIKA! Neural ∞-audio generation🎸
👉Novel neural music generation system on single consumer GPU!
😎Listen: https://bit.ly/3W80p4U
😎Paper arxiv.org/pdf/2208.08706.pdf
😎Code github.com/marcoppasini/musika
💓 Gesture Recognition in 80's 💓
👉The #Casio AT-550 was offering the edge gesture recognition in 1984!
😎Review https://bit.ly/3fcPia6
😎Clip: youtube.com/watch?v=piFaJmYpQfQ
📯Modeling the Human Pose Manifolds📯
👉#Meta Pose-NDF: continuous model for plausible human poses based on neural distance fields
😎Review https://bit.ly/3f6X59o
😎Paper arxiv.org/pdf/2207.13807.pdf
😎Project virtualhumans.mpi-inf.mpg.de/posendf
😎Code github.com/garvita-tiwari/PoseNDF
🛎️🛎️Autoregressive NeRF-Avatar🛎️🛎️
👉AutoAvatar by #Meta: autoregressive method for modeling dynamically deforming human bodies from raw scans
😎Review https://bit.ly/3W0oTgo
😎Paper arxiv.org/pdf/2203.13817.pdf
😎Project zqbai-jeremy.github.io/autoavatar
😎Code github.com/facebookresearch/AutoAvatar
↕️SOTA Action Detector @90+ FPS!↕️
👉YOWO-plus: real-time method for spatio-temporal action detection. YOWO-Nano the fastest!
😎Review https://bit.ly/3TUdhcI
😎Paper arxiv.org/pdf/2210.11219.pdf
😎Code github.com/yjh0410/PyTorch_YOWO
🤖JRBD: Egocentric Perception of Humans🤖
👉Stanford -> JRDB-Pose: Dataset with 600,000+ body pose annotations!
😎Review https://bit.ly/3gEZBE4
😎Paper arxiv.org/pdf/1910.11792.pdf
😎Project jrdb.erc.monash.edu/
🤯 Full-Body from head/hand signals 🤯
👉#Meta unveils AvatarPoser: first full-body pose method via user’s head/hands
😎Review https://bit.ly/3gESR9y
😎Paper arxiv.org/pdf/2207.13784.pdf
😎Code github.com/eth-siplab/AvatarPoser
🎨 UniColor: Unified Colorization 🎨
👉The first unified framework for colorization via stroke, exemplar, text, and a mix of them
😎Review https://bit.ly/3gESR9y
😎Paper arxiv.org/pdf/2209.11223.pdf
😎Project luckyhzt.github.io/unicolor
😎Code (SOON)
🔥New SOTA in Panoptic Segmentation🔥
👉#Google (with Hinton🤯) unveils Pix2Seq-D: novel generalist framework for panoptic segmentation
😎Review https://bit.ly/3DmpbGM
😎Paper arxiv.org/pdf/2210.06366.pdf
🦙LaMAR: Localization/Mapping for #AR🦙
👉A new benchmark for #AR in large and unconstrained scenes
😎Review https://bit.ly/3DjlnWU
😎Paper lamar.ethz.ch/files/LaMAR.pdf
😎Project https://lamar.ethz.ch/
😎Code github.com/microsoft/lamar-benchmark
🪂 Parallel NeRF for 6-DoF pose 🪂
👉#Nvidia unveils a parallel NeRF for 6-DoF target pose estimation
😎Review https://bit.ly/3guWWwA
😎Paper arxiv.org/pdf/2210.10108.pdf
😎Project https://pnerfp.github.io/
🔥Meta Omni3D: code is out!🔥
👉Source Code, models, and data just released by #META !
😎Review https://bit.ly/3MIWxD9
😎Paper arxiv.org/pdf/2207.10660.pdf
😎Project garrickbrazil.com/omni3d/
😎Code github.com/facebookresearch/omni3d
🔥 Dressing Avatars by #META 🔥
👉Novel deep photorealistic appearance method for physically-simulated clothing in #metaverse
😎Review https://bit.ly/3yRBW9Y
😎Paper arxiv.org/pdf/2206.15470.pdf
⚽Markerless Body-Object Interaction⚽
👉Novel whole-bodies/objects interaction method from multi-view RGB-D data
😎Review https://bit.ly/3yO56GY
😎Data intercap.is.tue.mpg.de/login.php
😎Project https://intercap.is.tue.mpg.de
😎Code github.com/YinghaoHuang91
😎Paper intercap.is.tue.mpg.de/media/upload/main.pdf
⛽ Stable Diffusion in #Blender ⛽
👉Render with SuperPowers: novel scene render via text prompt
😎Review https://bit.ly/3s1mEeN
😎Code github.com/benrugg/AI-Render
🪲#6D estimation fully in the wild🪲
👉First ever self-supervised 6D pose estimation training in the wild
😎Review https://bit.ly/3yHdHuS
😎Paper arxiv.org/pdf/2210.07199.pdf
😎Project kywind.github.io/self-pose
😎Code (soon)
🧮 Novel DM for 3D Shapes by #Nvidia 🧮
👉Hierarchical Latent Point Diffusion Model (LION) for 3D shape generation
😎Review https://bit.ly/3yDhZ6I
😎Paper arxiv.org/pdf/2210.06978.pdf
😎Project https://nv-tlabs.github.io/LION/
😎Code(soon) github.com/nv-tlabs/LION
🦑 Instant Map-free Relocalization 🦑
👉#Niantic unveils a novel instant, metric scaled re-localization with one single photo
😎Review https://bit.ly/3S1Gdyh
😎Paper arxiv.org/pdf/2210.05494.pdf
😎Project research.nianticlabs.com/mapfree-reloc-benchmark
😎Data research.nianticlabs.com/mapfree-reloc-benchmark/dataset
