ICCV重要论文一览文档格式.docx
《ICCV重要论文一览文档格式.docx》由会员分享,可在线阅读,更多相关《ICCV重要论文一览文档格式.docx(13页珍藏版)》请在冰豆网上搜索。
10.MichiganStateUniversity:
IlluminatingPedestriansviaSimultaneousDetection&
Segmentation行人检测分割
11.TheUniversityofNottingham:
BinarizedConvolutionalLandmarkLocalizersforHumanPoseEstimationandFaceAlignmentwithLimitedResources人体检测
12.UniversityofSurreyGuildford:
SubUNets:
End-to-endHandShapeandContinuousSignLanguageRecognitionCNN+LSTM端到端的手语识别
13.CMU:
OneNetworktoSolveThemAll—SolvingLinearInverseProblemsusingDeepProjectionModels图像修复
14.南理工(南大):
AdversarialPoseNet:
AStructure-awareConvolutionalNetworkforHumanPoseEstimation人姿态估计
15.IntelLabs:
FastImageProcessingwithFully-ConvolutionalNetworks,图片的后期处理,爱摄像的可以看
16.北航:
Look,PerceiveandSegment:
FindingtheSalientObjectsinImages
viaTwo-streamFixation-SemanticCNNsSOD目标检测
17.港中文(腾训优图):
Makeup-Go:
BlindReversionofPortraitEdit照片去美化,人像还原
18.UniversityofSouthernCalifornia:
Query-guidedRegressionNetworkwithContextPolicyforPhraseGrounding图像描述
19.国立清华(微软亚洲研究院):
Show,AdaptandTell:
AdversarialTrainingofCross-domainImageCaptioner图像转文字
20.清华:
SurfaceNormalsintheWild表面方向单目图像的深度估计
21.清华:
SegFlow:
JointLearningforVideoObjectSegmentationandOpticalFlow视频分割光流算法
22.中科大(港中文):
OnlineMulti-ObjectTrackingUsingCNN-basedSingleObjectTrackerwithSpatial-TemporalAttentionMechanism目标跟踪
23.InstituteofMathematicsoftheRomanianAcademy:
Unsupervisedlearningfromvideotodetectforegroundobjectsinsingleimages目标检测
24.GoogleBrain:
PixelRecursiveSuperResolution超分辨率
25.MicrosoftResearchAsia:
DeformableConvolutionalNetworks
26.港中文:
TowardsDiverseandNaturalImageDescriptionsviaaConditionalGAN对抗网络对图像的理解
,image-caption
27GeorgiaInstituteofTechnology:
LearningCooperativeVisualDialogAgentswithDeepReinforcementLearning协作对话
28.ImperialCollegeLondon:
SemanticImageSynthesisviaAdversarialLearning用自然语言描述图像合成
29.Inria:
BlitzNet:
AReal-TimeDeepNetworkforSceneUnderstanding场景分割贝叶斯网络
30.CMU:
Cut,PasteandLearn:
SurprisinglyEasySynthesisforInstanceDetection小数据集对物体进行识别
31.美图:
ParallelTrackingandVerifying:
AFrameworkforReal-TimeandHighAccuracyVisualTracking跟踪蛮好的
实用
32.GrazUniversityofTechnology(奥地利):
DetecttoTrackandTracktoDetect目标检测与跟踪(给了github进去却是空的,有点可惜)
33.MPIforIntelligentSystems:
SemanticVideoCNNsthroughRepresentationWarping视频语义分析
34.CMU:
LearningBackground-AwareCorrelationFiltersforVisualTracking跟踪
35.CMU:
NeedforSpeed:
ABenchmarkforHigherFrameRateObjectTracking高速跟踪的基准
36.中科大:
AMultimodalDeepRegressionBayesianNetworkforAffectiveVideoContentAnalyses深度回归贝叶斯的视频情感分析
37.清华:
VQS:
LinkingSegmentationstoQuestionsandAnswersforSupervisedAttentioninVQAandQuestion-FocusedSemanticSegmentation图像分割+语义理解
38.UniversityofTexasatAustin:
On-DemandLearningforDeepImageRestoration图像复原
39.UniversityofSouthernCalifornia:
TALL:
TemporalActivityLocalizationviaLanguageQuery通过语言查询进行时态活动定位
?
40.CSDepartmentStanfordUniversity:
Fine-grainedRecognitionintheWild:
AMulti-TaskDomainAdaptationApproach野外物体识别李飞飞的
41.NanyangTechnologicalUniversity:
AnEmpiricalStudyofLanguageCNNforImageCaptioning图像语义
42.天大:
LearningDynamicSiameseNetworkforVisualObjectTracking追踪
43.UniversityofIllinois,Urbana-Champaign:
AlignedImage-WordRepresentationsImproveInductiveTransferAcross
Vision-LanguageTasks视觉问答
44.StanfordUniversity:
CharacterizingandImprovingStabilityinNeuralStyleTransfer画风转换李飞飞
45.UniversityPolitehnicaofBucharest:
Unsupervisedobjectsegmentationinvideobyselectionofhighlyprobablepositivefeatures图像分割
46.香港大学:
SCNet:
LearningSemanticCorrespondence语义对应
47.西交大:
ChannelPruningforAcceleratingVeryDeepNeuralNetworks修剪深网络孙剑
48.FacebookAIResearch:
MaskR-CNN好像性能可以和fasterRCNN媲美VIP
49.UCBerkeley:
LocalizingMomentsinVideowithNaturalLanguage视频语义
,根据自然语言来定位视频中的片断
50.TheUniversityofTokyo:
JointDetectionandRecountingofAbnormalEventsbyLearningDeepGenericKnowledge图像语义
51.UniversityofCalifornia:
LearningtoReason:
End-to-EndModuleNetworksforVisualQuestionAnswering视觉问答
52.北大:
CenteredWeightNormalizationinAcceleratingTrainingofDeepNeuralNetworks对网络权重进行重新规划
53.CMU:
LearningPoliciesforAdaptiveTrackingwithDeepFeatureCascades跟踪
(好几篇CMU的跟踪方面的论文)
54.国科大:
Wavelet-SRNet:
AWavelet-basedCNNforMulti-scaleFaceSuperResolution人脸超分辨率
55.UniversityofCalifornia:
SceneParsingwithGlobalContextEmbedding图像分割
56.ETHZurich:
DSLR-Quality(单反相机图像质量)PhotosonMobileDeviceswithDeepConvolutionalNetworks学习提高照片的质量
57NUSGraduateSchoolforIntegrativeScienceandEngineering:
VideoSceneParsingwithPredictiveFeatureLearning
视频情景解析
58.StanfordUniversity:
InferringandExecutingProgramsforVisualReasoning情景推理李飞飞
59.RochesterInstituteofTechnology:
AnAnalysisofVisualQuestionAnsweringAlgorithms视觉问答
60.Jointlearningofobjectandactiondetectors物体跟踪与动作识别
61.TelAvivUniversity:
TemporalTessellation:
AUnifiedApproachforVideoAnalysis视频语义分析
62.UniversityofMannheim:
Higher-OrderMinimumCostLiftedMulticutsforMotionSegmentation物体分割
63.KoreaUniversity:
CDTS:
CollaborativeDetection,Tracking,andSegmentationforOnlineMultipleObjectSegmentationinVideos视频检测分割
64.Twitter:
FastFace-swapUsingConvolutionalNeuralNetworks快速换脸,好像蛮有意思的
65.StanfordUniversity:
Dense-CaptioningEventsinVideos视频语义能上下文李飞飞
videocaption,可用在视频检索,关键帧定位
66.NationalUniversityofSingapore:
Dual-GlanceModelforDecipheringSocialRelationships图片中的社会关系在图像语义理解时可能有用
67.港中文:
Identity-AwareTextual-VisualMatchingwithLatentCo-attention图片与句子描述之间的相识度
68.大连理工:
IsSecond-orderInformationHelpfulforLarge-scaleVisualRecognition?
关于卷积神经网深层信息
69.SnapInc(阅后即焚应用),雅虎,谷歌:
LearningfromNoisyLabelswithDistillation从杂乱标签中学习,对标注不精确
70.港中文:
LearningtoDisambiguatebyAskingDiscriminativeQuestions消除回答奇异的方法,关于VQA
71.成电:
LeveragingWeakSemanticRelevanceforComplexVideoEventClassification视频事件分析
72.港中文:
SceneGraphGenerationfromObjects,PhrasesandRegionCaptions图像语义
73.港中文:
SituationRecognitionwithGraphNeuralNetworks识别情景
74.清华:
RecurrentTopic-TransitionGANforVisualParagraphGeneration对抗网络来进行语义生成
75.深圳大学(港中文):
CascadedFeatureNetworkforSemanticSegmentationofRGB-DImages图像语义分割
76.港中文(商汤):
HydraPlus-Net:
AttentiveDeepFeaturesforPedestrianAnalysis人姿态分析
77.商汤(港中文):
RecurrentScaleApproximationforObjectDetectioninCNN目标的多尺度检测汤晓鸥
78.中科院:
ReferringExpressionGenerationandComprehensionviaAttributes通过索引产生语义
79.FacebookAIResearch:
PredictingDeeperintotheFutureofSemanticSegmentation预测语义
80.中山大学:
DeepDualLearningforSemanticImageSegmentation语义理解减少对标签数据的依赖
81.UniversityofIllinoisatUrbana-Champaign:
RecurrentModelsforSituationRecognition情景识别
82.UniversityofZurich:
Rotationequivariantvectorfieldnetworkscnn+旋转变化
83.IITHyderabad:
AttentiveSemanticVideoGenerationusingCaptions文字生成视频
聊天场景可以用?
84.Bosch:
UniversalAdversarialPerturbationsAgainstSemanticImageSegmentation加噪声对图像分割
85.POSTECH:
MarioQA:
AnsweringQuestionsbyWatchingGameplayVideos通过游戏视频进行QA
86.IIIT-Delhi:
FaceSketchMatchingviaCoupledDeepTransformLearning人脸与素描的匹配
87.UniversityofMaryland:
SSH:
SingleStageHeadlessFaceDetector数脸
88.YonseiUniversity:
ModellingtheSceneDependentImaginginCameraswithaDeepNeuralNetwork用深度学习改进照片的质量
89.MapillaryResearch:
TheMapillaryVistasDatasetforSemanticUnderstandingofStreetScenes街头情景语义理解
90.阿里(西电,西交):
HierarchicalMultimodalLSTMforDenseVisual-SemanticEmbedding语义理解
(想做视频匹配?
视频分类?
)
91.MITCSAIL:
PersonalizedCinemagraphsusingSemanticUnderstandingandCollaborativeLearning语义理解和协作学习
,个性化电影动图?
是否有可以玩的地方?
92.UniversityofSouthernCalifornia:
RealisticDynamicFacialTexturesfromaSingleImageusingGANs用对抗网络进行面部纹理处理
(去皱纹?
变老?
化妆?
93.MaxPlanckInstituteforInformaticsSaarlandInformaticsCampusSaabrucken:
TowardsaVisualPrivacyAdvisor:
UnderstandingandPredictingPrivacyRisksinImages图像关于隐私
94.AristotleUniversityofThessalonikiThessalonik:
LearningBag-of-FeaturesPoolingforDeepConvolutionalNeuralNetworks提出一种新的卷积BoF
95.Weakly-supervisedlearningofvisualrelations视觉关联弱监督学习,和语义有部分相关
96.UniversityofIllinoisatUrbana-Champaign:
PhraseLocalizationandVisualRelationshipDetectionwithComprehensiveImage-LanguageCues图像语义
97.IMEC,Belgium:
EncoderBasedLifelongLearning终身学习好像蛮有意思的
,模拟人?
98.TechnischeUniversitatMunich:
LearninginanUncertainWorld:
RepresentingAmbiguityThroughMultipleHypotheses预测不确定表达
99.MaxPlanckInstituteforIntelligentSystems:
EnhanceNet:
SingleImageSuper-ResolutionThroughAutomatedTextureSynthesis超分辨率纹理
100.UniversityofMaryland:
GuidedPerturbations:
Self-correctiveBehaviorinConvolutionalN