Table of Contents

• LatentKeypointGAN: Controlling Images via Latent KeypointsXingzhe He, Bastian Wandt, Helge Rhodin. 1-8 [doi]
• Towards Low-Cost Learning-based Camera ISP via Unrolled OptimizationAli Mosleh 0003, Marzieh S. Tahaei, James J. Clark, Vahid Partovi Nia. 9-18 [doi]
• A Reversible Transformer for LiDAR Point Cloud Semantic SegmentationPerpetual Hope Akwensi, Ruisheng Wang. 19-28 [doi]
• Continuous-Time Range-Only Pose EstimationAbhishek Goudar, Timothy D. Barfoot, Angela P. Schoellig. 29-36 [doi]
• Towards Open World NeRF-Based SLAMDaniil Lisus, Connor Holmes, Steven Lake Waslander. 37-44 [doi]
• Sparse Shape Encoding for Topologically Improved Instance SegmentationKeyi Liu, James H. Elder. 45-54 [doi]
• What does the Occluding Contour Tell us about Quantitative Shape?Yiming Qian, James H. Elder. 55-62 [doi]
• Evaluating 3D Shape Analysis Methods for Robustness to Rotation InvarianceSupriya Gadi Patil, Angel X. Chang, Manolis Savva. 63-72 [doi]
• InterTrack: Interaction Transformer for 3D Multi-Object TrackingJohn Willes, Cody Reading, Steven L. Waslander. 73-80 [doi]
• Along Similar Lines: Local Obstacle Avoidance for Long-Term Autonomous Path FollowingJordy Sehn, Yuchen Wu 0001, Timothy D. Barfoot. 81-88 [doi]
• aUToLights: A Robust Multi-Camera Traffic Light Detection and Tracking SystemSean Wu, Nicole Amenta, Jiachen Zhou, Sandro Papais, Jonathan Kelly. 89-96 [doi]
• Generalized Kronecker-based Adapters for Parameter-efficient Fine-tuning of Vision TransformersAli Edalati, Marawan Gamal Abdel Hameed, Ali Mosleh 0003. 97-104 [doi]
• Learning-to-Count by Learning-to-RankAdriano C. D' Alessandro, Ali Mahdavi-Amiri, Ghassan Hamarneh. 105-112 [doi]
• Kaskade-CNN and NB-KDE-CNN: CNN Architectures with KDE and Probabilistic Reasoning LayersMichael Cormier. 113-120 [doi]
• Class Instance Balanced Learning for Long-Tailed ClassificationMarc-Antoine Lavoie, Steven L. Waslander. 121-128 [doi]
• Transformer-Based Human Action Recognition with Dynamic Feature SelectionSoufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier. 129-136 [doi]
• ProPanDL: A Modular Architecture for Uncertainty-Aware Panoptic SegmentationJacob Deery, Chang Won Lee, Steven L. Waslander. 137-144 [doi]
• Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image DataAndrej Janda, Brandon Wagstaff, Edwin G. Ng, Jonathan Kelly. 145-152 [doi]
• Real-Time Instance Segmentation with Polygons Using an Intersection-Over-Union LossKatia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau. 153-160 [doi]
• Next-Best-View Selection for Robot Eye-in-Hand CalibrationJun Yang, Jason Rebello, Steven L. Waslander. 161-168 [doi]
• Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian DetectionAndrew Farley, Mohsen Zand, Michael A. Greenspan. 169-176 [doi]
• Local Region-to-Region Mapping-based Approach to Classify Articulated ObjectsAyush Aggarwal, Rustam Stolkin, Naresh Marturi. 177-183 [doi]
• Multi-Object Tracking and Segmentation with a Space-Time Memory NetworkMehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier. 184-193 [doi]
• Deformation Modeling for the Robotic Manipulation of 3D Elastic Objects using Physics-Informed Graph Neural NetworksAngel J. Valencia, Pierre Payeur. 194-201 [doi]
• Living in a Material World: Learning Material Properties from Full-Waveform Flash Lidar Data for Semantic SegmentationAndrej Janda, Pierre Merriaux, Pierre Olivier, Jonathan Kelly. 202-207 [doi]
• Naive Scene Graphs: How Visual is Modern Visual Relationship Detection?David Abou Chacra, John S. Zelek. 208-216 [doi]
• HyperMODEST: Self-Supervised 3D Object Detection with Confidence Score FilteringJenny Xu, Steven L. Waslander. 217-224 [doi]
• Adaptive Multiple Distributed Bidirectional Spiral Path Planning for Foraging Robot SwarmsQi Lu, Ryan Luna. 225-232 [doi]
• Robust Scuba Diver Tracking and Recovery in Open Water Using YOLOv7, SORT, and Spiral SearchFaraz Lotfi, Khalil Virji, Gregory Dudek. 233-240 [doi]
• CANDID: Correspondence AligNment for Deep-burst Image DenoisingArijit Mallick, Raphael Braun, Hendrik P. A. Lensch. 241-247 [doi]
• Hyperspectral Image Compression Using Implicit Neural RepresentationsShima Rezasoltani, Faisal Z. Qureshi. 248-255 [doi]
• Enhancing Satellite Trail Detection in Night Sky Imagery with Automatic Salience ThresholdingNikolaus Kollo, Yasushi Akiyama, Jiju Peethambaran. 256-264 [doi]
• Empirical Thresholding on Spatio-Temporal Autoencoders Trained on Surveillance Videos in a Dementia Care UnitShehroz S. Khan, Pratik K. Mishra, Bing Ye, Kristine Newman, Andrea Iaboni, Alex Mihailidis. 265-272 [doi]
• CrossMoCo: Multi-Modal Momentum Contrastive Learning for Point CloudSneha Paul, Zachary Patterson, Nizar Bouguila. 273-280 [doi]
• Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and RobustnessZahra Golpayegani, Patrick St-Amant, Nizar Bouguila. 281-287 [doi]
• Rehabilitation Exercise Repetition Segmentation and Counting Using Skeletal Body JointsAli Abedi 0001, Paritosh Bisht, Riddhi Chatterjee, Rachit Agrawal, Vyom Sharma, Dinesh Babu Jayagopi, Shehroz S. Khan. 288-295 [doi]
• Fast Fine-Tuning Using Curriculum Domain AdaptationLulan Shen, Ibtihel Amara, Ruofeng Li, Brett H. Meyer, Warren J. Gross, James J. Clark. 296-303 [doi]
• Gradient-Based Maximally Interfered Retrieval for Domain Incremental 3D Object DetectionBarza Nisar, Hruday Vishal Kanna Anand, Steven L. Waslander. 304-311 [doi]
• Tree Health Assessment from UAV Images: Improving Object Detection and Classification Using Hard Negative Mining and Semi-Supervised AutoencoderHela Jemaa, Wassim Bouachir, Brigitte Leblon, Armand LaRocque, Ata Haddadi, Nizar Bouguila. 312-319 [doi]
• Few-Shot Personality-Specific Image Captioning via Meta-LearningMehrdad Hosseinzadeh, Yang Wang 0003. 320-327 [doi]