{"total":15,"rows":[{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2111.13424","title":"ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics","created":"2021-11-26","cited_by_count":36,"area":null},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"area":null},{"id":"2304.06600","title":"Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation","created":"2023-04-13","cited_by_count":29,"area":null},{"id":"2106.15711","title":"RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2107.00339","title":"Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding","created":"2021-07-01","cited_by_count":12,"area":null},{"id":"2109.04378","title":"Dynamic Modeling of Hand-Object Interactions via Tactile Sensing","created":"2021-09-09","cited_by_count":8,"area":null},{"id":"2301.04366","title":"Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering","created":"2023-01-11","cited_by_count":5,"area":null},{"id":"2302.04149","title":"Domain Adaptation of Synthetic Driving Datasets for Real-World Autonomous Driving","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2103.14103","title":"Discriminative Semantic Transitive Consistency for Cross-Modal Learning","created":"2021-03-25","cited_by_count":1,"area":null},{"id":"2202.09099","title":"AMS_ADRN at SemEval-2022 Task 5: A Suitable Image-text Multimodal Joint Modeling Method for Multi-task Misogyny Identification","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2302.01976","title":"SPARLING: Learning Latent Representations with Extremely Sparse Activations","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2311.03866","title":"SCONE-GAN: Semantic Contrastive learning-based Generative Adversarial Network for an end-to-end image translation","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2609.03516","title":"Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object Detection","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}