Papers

1. Sparse-shot Learning with Exclusive Cross-Entropy for Extremely Many Localisations

2. Project RISE: Recognizing Industrial Smoke Emissions

3. Improving Aleatoric Uncertainty Quantification in Multi-Annotated Medical Image Segmentation with Normalizing Flows

4. Depth estimation from a single CD-SEM image using domain adaptation with multimodal data

5. Proximally Sensitive Error for Anomaly Detection and Feature Learning

6. ChickenNet - an end-to-end approach for plumage condition assessment of laying hens in commercial farms using computer vision

7. Combining traffic light detection with the correct behavior via end-to-end learning

8. Spectral Leakage and Rethinking the Kernel Size in CNNs

9. Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types

10. Fully Automated Thrombus Segmentation on CT Images of Patients with Acute Ischemic Stroke

11. No frame left behind: Full Video Action Recognition

12. Long-term Behaviour Recognition in Videos with Actor-focused Region Attention

13. Equidistant Hyperspherical Prototypes Improve Uncertainty Quantification

14. Audio-Adaptive Activity Recognition Across Video Domains

15. Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation

16. Resolution learning in deep convolutional networks using scale-space theory

17. Zero-Shot Action Recognition from Diverse Object-Scene Compositions

18. A Deep Learning Approach to Assist Sustainability of Demersal Trawling Operations

19. Real-time webcam heart-rate and variability estimation with clean ground truth for evaluation

20. Part-aware Panoptic Segmentation

21. A survey of computational methods for iconic image analysis

22. Automatic Calibration of the Fisheye Camera for Egocentric 3D Human Pose Estimation from a Single Image

23. Deep Vanishing Point Detection: Geometric priors make dataset variations vanish

24. Respecting Domain Relations: Hypothesis Invariance for Domain Generalization

25. Multi-Loss Weighting with Coefficient of Variations

26. Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels

27. Self-Contained Entity Discovery from Captioned Videos

28. DISCO: accurate Discrete Scale Convolutions

29. Hyperbolic Busemann Learning with Ideal Prototypes

30. AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift

31. Neural Feature Matching in Implicit 3D Representations

1. Towards a Human in the Loop Approach to Preserve Privacy in Images

2. Roto-translated Local Coordinate Frames For Interacting Dynamical Systems

3. Efficiency in Real-time Webcam Gaze Tracking

4. T-LEAP: Occlusion-robust pose estimation of walking cows using temporal information

5. Skip-Convolutions for Efficient Video Processing

6. Deep continuous networks

7. Self-Supervised Road Layout Parsing with Graph Auto-Encoding

8. Semantic Segmentation: How to Train for The Wild

9. Critical Vehicle Detection for Intelligent Transportation Systems

10. On Sensitive Minima in Margin-Based Deep Distance Learning

11. Hyperbolic Image Segmentation

12. On Measuring and Controlling the Spectral Bias of the Deep Image Prior

13. Kinship identification through joint learning using kinship verification ensembles

14. FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes

15. On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location

16. Multiresolution Knowledge Distillation for Anomaly Detection

17. Zero-Shot Day-Night Domain Adaptation with a Physics Prior

18. Enhancing Classifier Conservativeness and Robustness by Polynomiality

19. Video-Based Detection and Tracking with Improved Re-identification Association for Pigs and Laying Hens in Farms

20. PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition

21. Continual Learning of Dynamical Systems with Competitive Multi-Head Reservoir Computing

22. BoxeR: Box-Attention for 2D and 3D Transformers

23. PointMixup: Augmentation for Point Clouds

24. Less than Few: Self-Shot Video Instance Segmentation