<kbd id="afajh"><form id="afajh"></form></kbd>
<strong id="afajh"><dl id="afajh"></dl></strong>
    <del id="afajh"><form id="afajh"></form></del>
        1. <th id="afajh"><progress id="afajh"></progress></th>
          <b id="afajh"><abbr id="afajh"></abbr></b>
          <th id="afajh"><progress id="afajh"></progress></th>

          ECCV22 最新54篇論文分方向整理|包含Transformer、圖像處理、人臉等(附下載)

          共 9762字,需瀏覽 20分鐘

           ·

          2022-07-31 02:40

          點擊上方視學算法”,選擇加"星標"或“置頂

          重磅干貨,第一時間送達

          本文首發(fā)極市平臺公眾號,轉(zhuǎn)載請獲得授權(quán)并標明出處。

          導讀

           

          最近一周,ECCV2022陸續(xù)放出了更多和GAN,Transformers相關(guān)的論文,為了讓大家及時獲取和學習到計算機視覺前沿技術(shù),極市對最新一批論文進行整理(新增54篇),包括分研究方向的論文及代碼匯總。 

          ECCV 2022 論文分方向整理目前在極市社區(qū)持續(xù)更新中,已累計更新了108篇,項目地址:https://github.com/extreme-assistant/ECCV2022-Paper-Code-Interpretation

          以下是本周更新的 ECCV 2022 論文,包含圖像處理,Transformers,人臉,弱監(jiān)督學習,模型訓練泛化等方向。

          點擊 閱讀原文 即可打包下載。

          檢測

          2D目標檢測

          [1] Multimodal Object Detection via Probabilistic Ensembling (基于概率集成的多模態(tài)目標檢測) (Oral)
          paper:https://arxiv.org/abs/2104.02904
          code:https://github.com/Jamie725/RGBT-detection

          3D目標檢測

          [1] Densely Constrained Depth Estimator for Monocular 3D Object Detection (用于單目 3D 目標檢測的密集約束深度估計器)
          paper:https://arxiv.org/abs/2207.10047
          code:https://github.com/bravegroup/dcd

          人物交互檢測

          [1] Discovering Human-Object Interaction Concepts via Self-Compositional Learning (通過自組合學習發(fā)現(xiàn)人-物交互概念)
          paper:https://arxiv.org/abs/2203.14272
          code:https://github.com/zhihou7/scl; https://github.com/zhihou7/HOI-CL

          分割

          實例分割

          [1] In Defense of Online Models for Video Instance Segmentation (為視頻實例分割的在線模型辯護) (Oral)
          paper:https://arxiv.org/abs/2207.10661
          code:https://github.com/wjf5203/vnext

          圖像處理

          超分辨率

          [1] Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution (學習高效圖像超分辨率的串并行查找表)
          paper:https://arxiv.org/abs/2207.12987
          code:https://github.com/zhjy2016/splut
          [2] Efficient Meta-Tuning for Content-aware Neural Video Delivery (內(nèi)容感知神經(jīng)視頻交付的高效元調(diào)整)
          paper:https://arxiv.org/abs/2207.09691
          code:https://github.com/neural-video-delivery/emt-pytorch-eccv2022

          圖像復原/圖像增強/圖像重建

          [1] Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression (無監(jiān)督夜間圖像增強:當層分解遇到光效抑制時)
          paper:https://arxiv.org/abs/2207.10564
          code:https://github.com/jinyeying/night-enhancement
          [2] Bringing Rolling Shutter Images Alive with Dual Reversed Distortion(通過雙重反轉(zhuǎn)失真使?jié)L動快門圖像重現(xiàn)) (Oral)
          paper:https://arxiv.org/abs/2203.06451
          code:https://github.com/zzh-tech/dual-reversed-rs
          [3] Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression (無監(jiān)督夜間圖像增強:當層分解遇到光效抑制時)
          paper:https://arxiv.org/abs/2207.10564
          code:https://github.com/jinyeying/night-enhancement

          圖像去陰影/去反射

          [1] Deep Portrait Delighting (深度人像去光)
          paper:https://arxiv.org/abs/2203.12088)

          圖像去噪

          [1] Perceiving and Modeling Density is All You Need for Image Dehazing (感知和建模密度是圖像去霧所需的全部) (Oral)
          paper:https://arxiv.org/abs/2111.09733
          code:https://github.com/Owen718/Perceiving-and-Modeling-Density-is-All-You-Need-for-Image-Dehazing
          [2] Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance (來自模糊的動畫:具有運動引導的多模態(tài)模糊分解)
          paper:https://arxiv.org/abs/2207.10123
          code:https://github.com/zzh-tech/Animation-from-Blur

          視頻處理

          視頻修復

          [1] Error Compensation Framework for Flow-Guided Video Inpainting (流引導視頻修復的誤差補償框架) 
          paper:https://arxiv.org/abs/2207.10391

          視頻去模糊

          [1] Event-guided Deblurring of Unknown Exposure Time Videos (未知曝光時間視頻的事件引導去模糊) (Oral)
          paper:https://arxiv.org/abs/2112.06988
          [2] Efficient Video Deblurring Guided by Motion Magnitude (由運動幅度引導的高效視頻去模糊)
          paper:https://arxiv.org/abs/2207.13374
          code:https://github.com/sollynoay/mmp-rnn

          圖像&視頻檢索/視頻理解

          行為識別/行為識別/動作識別/檢測/分割

          [1] GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality (GaitEdge:超越普通的端到端步態(tài)識別,提高實用性)
          paper:https://arxiv.org/abs/2203.03972
          code:https://github.com/shiqiyu/opengait
          [2] Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition (用于跨域 3D 動作識別的協(xié)作域共享和特定于目標的特征聚類)
          paper:https://arxiv.org/abs/2207.09767
          code:https://github.com/canbaoburen/CoDT

          行人重識別/檢測

          [1] PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification(PASS:用于人員重新識別的部分感知自我監(jiān)督預訓練)
          paper:https://arxiv.org/abs/2203.03931
          code:https://github.com/casia-iva-lab/pass-reid

          圖像/視頻檢索

          [1] Feature Representation Learning for Unsupervised Cross-domain Image Retrieval (無監(jiān)督跨域圖像檢索的特征表示學習)
          paper:https://arxiv.org/abs/2207.09721
          code:https://github.com/conghuihu/ucdir
          [2] LocVTP: Video-Text Pre-training for Temporal Localization (LocVTP:時間定位的視頻文本預訓練)
          paper:https://arxiv.org/abs/2207.10362
          code:https://github.com/mengcaopku/locvtp

          估計

          視覺定位/位姿估計

          [1] 3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal (通過手部去遮擋和移除的 3D 交互手部姿勢估計)
          paper:https://arxiv.org/abs/2207.11061
          code:https://github.com/menghao666/hdr
          [2] Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration (基于隱式空間校準的 Transformer 的弱監(jiān)督目標定位)
          paper:https://arxiv.org/abs/2207.10447
          code:https://github.com/164140757/scm

          人臉

          [1] Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (通過場景消歧實現(xiàn)種族無偏膚色估計)
          paper:https://arxiv.org/abs/2205.03962
          code:https://trust.is.tue.mpg.de/
          [2] MoFaNeRF: Morphable Facial Neural Radiance Field (MoFaNeRF:可變形面部神經(jīng)輻射場)
          paper:https://arxiv.org/abs/2112.02308
          code:https://github.com/zhuhao-nju/mofanerf

          三維視覺

          三維重建

          [1] DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras (DiffuStereo:使用稀疏相機通過基于擴散的立體進行高質(zhì)量人體重建)
          paper:https://arxiv.org/abs/2207.08000

          場景重建/視圖合成/新視角合成

          [1] Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields (Sem2NeRF:將單視圖語義掩碼轉(zhuǎn)換為神經(jīng)輻射場)
          paper:https://arxiv.org/abs/2203.10821
          code:https://github.com/donydchen/sem2nerf

          目標跟蹤

          [1] Tracking Every Thing in the Wild (追蹤野外的每一件事)
          paper:https://arxiv.org/abs/2207.12978

          文本檢測/識別/理解

          [1] Contextual Text Block Detection towards Scene Text Understanding (面向場景文本理解的上下文文本塊檢測)
          paper:https://arxiv.org/abs/2207.12955
          [2] PromptDet: Towards Open-vocabulary Detection using Uncurated Images (PromptDet:使用未經(jīng)處理的圖像進行開放詞匯檢測)
          paper:https://arxiv.org/abs/2203.16513
          code:https://github.com/fcjian/PromptDet
          [3] End-to-End Video Text Spotting with Transformer (使用 Transformer 的端到端視頻文本定位) (Oral)
          paper:https://arxiv.org/abs/2203.10539
          code:https://github.com/weijiawu/transdetr

          GAN/生成式/對抗式

          [1] Learning Energy-Based Models With Adversarial Training (通過對抗訓練學習基于能量的模型)
          paper:https://arxiv.org/abs/2012.06568
          code:https://github.com/xuwangyin/AT-EBMs
          [2] Adaptive Image Transformations for Transfer-based Adversarial Attack (基于傳輸?shù)膶剐怨舻淖赃m應(yīng)圖像轉(zhuǎn)換)
          paper:https://arxiv.org/abs/2111.13844
          [3] Generative Multiplane Images: Making a 2D GAN 3D-Aware (生成多平面圖像:讓一個2D GAN變得3D感知)
          paper:https://arxiv.org/abs/2207.10642
          code:https://github.com/apple/ml-gmpi

          圖像生成/圖像合成

          [1] PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation (PixelFolder:用于圖像生成的高效漸進式像素合成網(wǎng)絡(luò))
          paper:https://arxiv.org/abs/2204.00833
          code:https://github.com/blinghe/pixelfolder

          視覺預測

          [1] D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights (D2-TPred:交通燈下軌跡預測的不連續(xù)依賴)
          paper:https://arxiv.org/abs/2207.10398
          code:https://github.com/vtp-tl/d2-tpred

          神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)設(shè)計

          DNN

          [1] Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips (使用 Bit Flips 對神經(jīng)網(wǎng)絡(luò)進行難以察覺的特洛伊木馬攻擊)
          paper:https://arxiv.org/abs/2207.13417
          code:https://github.com/jiawangbai/hpt

          Transformer

          [1] Improving Vision Transformers by Revisiting High-frequency Components (通過重新審視高頻組件來改進視覺變壓器)
          paper:https://arxiv.org/abs/2204.00993
          code:https://github.com/jiawangbai/HAT
          [2] Transformer with Implicit Edges for Particle-based Physics Simulation (用于基于粒子的物理模擬的隱式邊緣變壓器)
          paper:https://arxiv.org/abs/2207.10860
          code:https://github.com/ftbabi/tie_eccv2022
          [3] ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer (ScalableViT:重新思考 Vision Transformer 面向上下文的泛化)
          paper:https://arxiv.org/abs/2203.10790
          code:https://github.com/yangr116/scalablevit
          [4] Visual Prompt Tuning (視覺提示調(diào)整)
          paper:https://arxiv.org/abs/2203.12119
          code:https://github.com/KMnP/vpt

          圖像特征提取與匹配

          [1] Unsupervised Deep Multi-Shape Matching (無監(jiān)督深度多形狀匹配)
          paper:https://arxiv.org/abs/2207.09610

          視覺表征學習

          [1] Object-Compositional Neural Implicit Surfaces (對象組合神經(jīng)隱式曲面)
          paper:https://arxiv.org/abs/2207.09686
          code:https://github.com/qianyiwu/objsdf

          模型訓練/泛化

          長尾分布

          [1] Long-tailed Instance Segmentation using Gumbel Optimized Loss (使用 Gumbel 優(yōu)化損失的長尾實例分割)
          paper:https://arxiv.org/abs/2207.10936
          code:https://github.com/kostas1515/gol)
          [2] Identifying Hard Noise in Long-Tailed Sample Distribution (識別長尾樣本分布中的硬噪聲) (Oral)
          paper:https://arxiv.org/abs/2207.13378
          code:https://github.com/yxymessi/h2e-framework

          模型壓縮

          知識蒸餾

          [1] Prune Your Model Before Distill It (在蒸餾之前修剪你的模型)
          paper:https://arxiv.org/abs/2109.14960
          code:https://github.com/ososos888/prune-then-distill
          [2] Efficient One Pass Self-distillation with Zipf's Label Smoothing (使用 Zipf 的標簽平滑實現(xiàn)高效的單程自蒸餾)
          paper:https://arxiv.org/abs/2207.12980
          code:https://github.com/megvii-research/zipfls

          半監(jiān)督學習/弱監(jiān)督學習/無監(jiān)督學習/自監(jiān)督學習

          [1] Acknowledging the Unknown for Multi-label Learning with Single Positive Labels (用單個正標簽承認未知的多標簽學習)
          paper:https://arxiv.org/abs/2203.16219
          code:https://github.com/correr-zhou/spml-acktheunknown
          [2] W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection (W2N:目標檢測從弱監(jiān)督切換到嘈雜監(jiān)督)
          paper:https://arxiv.org/abs/2207.12104
          code:https://github.com/1170300714/w2n_wsod
          [3] CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation (CA-SSL:用于檢測和分割的與類別無關(guān)的半監(jiān)督學習)
          paper:https://arxiv.org/abs/2112.04966
          code:https://github.com/dvlab-research/Entity

          多模態(tài)學習/跨模態(tài)

          視覺-語言

          [1] Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting (語言問題:用于場景文本檢測和識別的弱監(jiān)督視覺語言預訓練方法) (Oral)
          paper:https://arxiv.org/abs/2203.03911

          小樣本學習/零樣本學習

          [1] Worst Case Matters for Few-Shot Recognition (最壞情況對少數(shù)鏡頭識別很重要)
          paper:https://arxiv.org/abs/2203.06574
          code:https://github.com/heekhero/ACSR

          持續(xù)學習

          [1] Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (通過持續(xù)學習中的高級零空間平衡穩(wěn)定性和可塑性) (Oral)
          paper:https://arxiv.org/abs/2207.12061
          [2] Online Continual Learning with Contrastive Vision Transformer (使用對比視覺轉(zhuǎn)換器進行在線持續(xù)學習)
          paper:https://arxiv.org/abs/2207.13516

          模仿學習

          [1] Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction (通過殘差動作預測解決視覺模仿學習中的模仿問題)
          paper:https://arxiv.org/abs/2207.09705


          點個在看 paper不斷!

          瀏覽 31
          點贊
          評論
          收藏
          分享

          手機掃一掃分享

          分享
          舉報
          評論
          圖片
          表情
          推薦
          點贊
          評論
          收藏
          分享

          手機掃一掃分享

          分享
          舉報
          <kbd id="afajh"><form id="afajh"></form></kbd>
          <strong id="afajh"><dl id="afajh"></dl></strong>
            <del id="afajh"><form id="afajh"></form></del>
                1. <th id="afajh"><progress id="afajh"></progress></th>
                  <b id="afajh"><abbr id="afajh"></abbr></b>
                  <th id="afajh"><progress id="afajh"></progress></th>
                  日韩国产高清无码 | 中文字幕在线欧美 | 成人伊人| 青青草成人视频在线播放 | 日本操B电影 |