
Open Domain Generalization with DomainAugmented MetaLearning
Leveraging datasets available to learn a model with high generalization ...
read it

PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
The predictive learning of spatiotemporal sequences aims to generate fut...
read it

Regressive Domain Adaptation for Unsupervised Keypoint Detection
Domain adaptation (DA) aims at transferring knowledge from a labeled sou...
read it

Cycle SelfTraining for Domain Adaptation
Mainstream approaches for unsupervised domain adaptation (UDA) learn dom...
read it

MotionRNN: A Flexible Model for Video Prediction with SpacetimeVarying Motions
This paper tackles video prediction from a new dimension of predicting s...
read it

SelfTuning for DataEfficient Deep Learning
Deep learning has made revolutionary advances to diverse applications in...
read it

LogME: Practical Assessment of Pretrained Models for Transfer Learning
This paper studies task adaptive pretrained model selection, an underex...
read it

GAHNE: GraphAggregated Heterogeneous Network Embedding
The realworld networks often compose of different types of nodes and ed...
read it

Event Data Quality: A Survey
Event data are prevalent in diverse domains such as financial trading, b...
read it

Bituning of Pretrained Representations
It is common within the deep learning community to first pretrain a dee...
read it

Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
This paper explores a new research problem of unsupervised transfer lear...
read it

On Localized Discrepancy for Domain Adaptation
We propose the discrepancybased generalization theories for unsupervise...
read it

Transferable Calibration with Lower Bias and Variance in Domain Adaptation
Domain Adaptation (DA) enables transferring a learning machine from a la...
read it

Learning Individual Models for Imputation (Technical Report)
Missing numerical values are prevalent, e.g., owing to unreliable sensor...
read it

Time Series Data Cleaning: From Anomaly Detection to Anomaly Repairing (Technical Report)
Errors are prevalent in time series data, such as GPS trajectories or se...
read it

Adversarial Pyramid Network for Video Domain Generalization
This paper introduces a new research problem of video domain generalizat...
read it

Less Confusion More Transferable: Minimum Class Confusion for Versatile Domain Adaptation
Domain Adaptation (DA) transfers a learning model from a labeled source ...
read it

Towards Understanding the Transferability of Deep Representations
Deep neural networks trained on a wide range of datasets demonstrate imp...
read it

Learning Stages: Phenomenon, Root Cause, Mechanism Hypothesis, and Implications
Under StepDecay learning rate strategy (decaying the learning rate after...
read it

Learning to Transfer Examples for Partial Domain Adaptation
Domain adaptation is critical for learning in new and unseen environment...
read it

Spatiotemporal Pyramid Network for Video Action Recognition
Twostream convolutional networks have shown strong performance in video...
read it

Deep Triplet Quantization
Deep hashing establishes efficient and effective image retrieval by end...
read it

Flexible Attributed Network Embedding
Network embedding aims to find a way to encode network by learning an em...
read it

Reversing TwoStream Networks with Decoding Discrepancy Penalty for Robust Action Recognition
We discuss the robustness and generalization ability in the realm of act...
read it

Memory In Memory: A Predictive Neural Network for Learning HigherOrder NonStationarity from Spatiotemporal Dynamics
Natural spatiotemporal processes can be highly nonstationary in many wa...
read it

Heterogeneous Replica for Query on Cassandra
Cassandra is a popular structured storage system with highperformance, ...
read it

MultiAdversarial Domain Adaptation
Recent advances in deep domain adaptation reveal that adversarial learni...
read it

Deep Priority Hashing
Deep hashing enables image retrieval by endtoend learning of deep repr...
read it

Partial Adversarial Domain Adaptation
Domain adversarial learning aligns the feature distributions across the ...
read it

Matching Consecutive Subpatterns Over Streaming Time Series
Pattern matching of streaming time series with lower latency under limit...
read it

PredRNN++: Towards A Resolution of the DeepinTime Dilemma in Spatiotemporal Predictive Learning
We present PredRNN++, an improved recurrent network for video predictive...
read it

Transfer Adversarial Hashing for Hamming Space Retrieval
Hashing is widely applied to largescale image retrieval due to the stor...
read it

Finegrained Pattern Matching Over Streaming Time Series
Pattern matching of streaming time series with lower latency under limit...
read it

KVmatch: An Efficient Subsequence Matching Approach for Large Scale Time Series
Time series data have exploded due to the popularity of new applications...
read it

HashNet: Deep Learning to Hash by Continuation
Learning to hash has been widely applied to approximate nearest neighbor...
read it

Deep Transfer Learning with Joint Adaptation Networks
Deep networks have been successfully applied to learn transferable featu...
read it

Correlation Hashing Network for Efficient CrossModal Retrieval
Hashing is widely applied to approximate nearest neighbor search for lar...
read it
Jianmin Wang
is this you? claim profile