| MTLDesc: Looking Wider to Describe Better | Mar 14, 2022 | Indoor LocalizationTriplet | CodeCode Available | 1 |
| MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes | Mar 10, 2022 | 3D dense captioningDense Captioning | CodeCode Available | 1 |
| Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection | Mar 5, 2022 | Camouflaged Object SegmentationImage Segmentation | CodeCode Available | 1 |
| Enhancing Adversarial Robustness for Deep Metric Learning | Mar 2, 2022 | Adversarial RobustnessMetric Learning | CodeCode Available | 1 |
| One-shot Scene Graph Generation | Feb 22, 2022 | Graph GenerationScene Graph Generation | CodeCode Available | 1 |
| Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics | Feb 1, 2022 | Human-Object Interaction DetectionObject | CodeCode Available | 1 |
| SURDS: Self-Supervised Attention-guided Reconstruction and Dual Triplet Loss for Writer Independent Offline Signature Verification | Jan 25, 2022 | Image ReconstructionMetric Learning | CodeCode Available | 1 |
| Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement | Jan 6, 2022 | DisentanglementDomain Adaptation | CodeCode Available | 1 |
| Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement | Dec 21, 2021 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | CodeCode Available | 1 |
| Fusion and Orthogonal Projection for Improved Face-Voice Association | Dec 20, 2021 | Cross-Modal RetrievalTriplet | CodeCode Available | 1 |
