ICCV重要论文一览文档格式.docx

上传人:b****3 文档编号:17059185 上传时间:2022-11-28 格式:DOCX 页数:13 大小:30.38KB
下载 相关 举报
ICCV重要论文一览文档格式.docx_第1页
第1页 / 共13页
ICCV重要论文一览文档格式.docx_第2页
第2页 / 共13页
ICCV重要论文一览文档格式.docx_第3页
第3页 / 共13页
ICCV重要论文一览文档格式.docx_第4页
第4页 / 共13页
ICCV重要论文一览文档格式.docx_第5页
第5页 / 共13页
点击查看更多>>
下载资源
资源描述

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。

ICCV重要论文一览文档格式.docx

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

展开阅读全文
相关资源
猜你喜欢
相关搜索

当前位置:首页 > 外语学习 > 法语学习

copyright@ 2008-2022 冰豆网网站版权所有

经营许可证编号:鄂ICP备2022015515号-1