53 results on '"Cheng-lin Liu"'
Search Results
2. Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information.
3. Happy: A Debiased Learning Framework for Continual Generalized Category Discovery.
4. Adapting Vision-Language Models to Open Classes via Test-Time Prompt Tuning.
5. StylePrompter: Enhancing Domain Generalization with Test-Time Style Priors.
6. CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models.
7. Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram.
8. WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models.
9. PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning.
10. Federated Class-Incremental Learning with Prototype Guided Transformer.
11. Towards Non-Exemplar Semi-Supervised Class-Incremental Learning.
12. Revisiting Confidence Estimation: Towards Reliable Failure Prediction.
13. Active Generalized Category Discovery.
14. Open-world Machine Learning: A Review and New Outlooks.
15. Ensemble Quadratic Assignment Network for Graph Matching.
16. Differentiable Proximal Graph Matching.
17. MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution.
18. Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning.
19. Unified Entropy Optimization for Open-Set Test-Time Adaptation.
20. Multi-scale Unified Network for Image Classification.
21. Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection.
22. OpenMix: Exploring Outlier Samples for Misclassification Detection.
23. Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning.
24. Unified Classification and Rejection: A One-versus-All Framework.
25. Rethinking Confidence Calibration for Failure Prediction.
26. A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram.
27. ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images.
28. LANS: A Layout-Aware Neural Solver for Plane Geometry Problem.
29. Dynamics-Aware Loss for Learning with Label Noise.
30. Towards Reliable Domain Generalization: A New Dataset and Evaluations.
31. Plane Geometry Diagram Parsing.
32. Replacing Backpropagation with Biological Plausible Top-down Credit Assignment in Deep Neural Networks Training.
33. Document Dewarping with Control Points.
34. Unsupervised Structure-Texture Separation Network for Oracle Character Recognition.
35. Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks.
36. Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network.
37. Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm.
38. Towards Robust Pattern Recognition: A Review.
39. ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition - RRC-MLT-2019.
40. Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation.
41. BlockQNN: Efficient Block-wise Neural Network Architecture Generation.
42. Anomaly Detection via Minimum Likelihood Generative Adversarial Networks.
43. Robust Classification with Convolutional Prototype Learning.
44. SCAN: Sliding Convolutional Attention Network for Scene Text Recognition.
45. Practical Network Blocks Design with Q-Learning.
46. Scene Text Recognition with Sliding Convolutional Character Models.
47. Deep Direct Regression for Multi-Oriented Scene Text Detection.
48. Natural Scene Character Recognition Using Robust PCA and Sparse Representation.
49. Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark.
50. Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.