10 accepted papers
Multi-robot coordination in shared workspaces is prone to deadlocks, which can compromise operational capabilities and task efficiency. Accurately determining the timing and spatial locations of deadlocks is essential for effective resolution, yet remains challenging due to dynamic robot interaction…
This work tackles a key challenge in test-time energy adaptation: prohibitive time overhead arising from recent state-of-the-art test-time adaptation (TTA) methods, which are built on energy models relying on iterative Monte Carlo or Langevin dynamics sampling with multiple stochastic updates per te
Source-free unsupervised domain adaptation (SF-UDA), which relies only on a pre-trained source model and unlabeled target data, has gained significant attention. Pseudo-labeling, valued for its simplicity and effectiveness, is a key approach in SF-UDA. However, existing methods neglect the consisten
We propose an integrated learning scheme of Video Super-Resolution and Enhancement in Low-Light environment, named VSRELL, which aims to recover Well-Illuminated High-Resolution (WIHR) sequence from Low-Light Low-Resolution (LLLR) counterparts. Due to the complex coupling of multiple degradations, t
Manta ray-inspired robots exhibit broad application prospects. In nature, different manta rays possess different stiffness of pectoral fins to survive in specific environment. Some rays present stiffer fins that enable an oscillation, achieving large propulsion to adapt to a pelagic lifestyle. While
Time Series Anomaly Detection (TSAD) methods often require large datasets and extensive domain knowledge, limiting their effectiveness in data-scarce environments. We introduce a novel unsupervised TSAD approach based on path signatures, which efficiently extracts shape features from time series dat…
While model quantization has become pivotal for deploying super-resolution (SR) networks on mobile devices, existing works focus on quantization methods only for image super-resolution. Different from image super-resolution, the temporal error propagation, shared temporal parameterization, and tempo…
Biological manta rays alter the projected area of their pectoral fins during flapping, achieve different flapping strokes to adjust dynamic generation, such as holding, rising, sinking and rolling strokes. Manta ray-inspired robots possess high motion efficiency and stability, exhibiting broad prosp
Delivering precise point and distributional forecasts across a spectrum of prediction horizons represents a significant and enduring challenge in the application of time-series forecasting within various industries. Prior research on developing deep learning models for time-series forecasting has of…
Traditional Time-series Anomaly Detection (TAD) methods often struggle with the composite nature of complex time-series data and a diverse array of anomalies. We introduce TADNet, an end-to-end TAD model that leverages Seasonal-Trend Decomposition to link various types of anomalies to specific decom…