Related papers: Minimizing the Motion-to-Photon-delay (MPD) in Vir…
Subsequence Dynamic Time Warping (sDTW) is the metric of choice when performing many sequence matching and alignment tasks. While sDTW is flexible and accurate, it is neither simple nor fast to compute; significant research effort has been…
To extend the application of vision-language models (VLMs) from web images to sensor-mediated physical environments, we propose Multi-View Physical-prompt for Test-Time Adaptation (MVP), a forward-only framework that moves test-time…
Adaptive optimizers like AdamW apply uniform hyperparameters across all parameter groups, ignoring heterogeneous optimization dynamics across layers and modules. We address this limitation by proposing MetaAdamW - a new optimizer that…
Many time series data mining problems can be solved with repeated use of distance measure. Examples of such tasks include similarity search, clustering, classification, anomaly detection and segmentation. For over two decades it has been…
Atmospheric Turbulence (AT) degrades the clarity and accuracy of surveillance imagery, posing challenges not only for visualization quality but also for object classification and scene tracking. Deep learning-based methods have been…
The Vision Transformer (ViT) architecture has established its place in computer vision literature, however, training ViTs for RGB-D object recognition remains an understudied topic, viewed in recent literature only through the lens of…
Foundation models, exemplified by GPT technology, are discovering new horizons in artificial intelligence by executing tasks beyond their designers' expectations. While the present generation provides fundamental advances in understanding…
Convolutional neural networks have enabled accurate image super-resolution in real-time. However, recent attempts to benefit from temporal correlations in video super-resolution have been limited to naive or inefficient architectures. In…
The rising demand for high quality display has ensued active research in high dynamic range (HDR) imaging, which has the potential to replace the standard dynamic range imaging. This is due to HDR's features like accurate reproducibility of…
Embodied world models aim to predict and interact with the physical world through visual observations and actions. However, existing models struggle to accurately translate low-level actions (e.g., joint positions) into precise robotic…
Proactive tile-based video streaming can avoid motion-to-photon latency of wireless virtual reality (VR) by computing and delivering the predicted tiles to be requested before playback. All existing works either focus on designing…
Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this…
Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL…
Multi-Task Learning (MTL) is a foundational machine learning problem that has seen extensive development over the past decade. Recently, various optimization-based MTL approaches have been proposed to learn multiple tasks simultaneously by…
Text-guided video prediction (TVP) involves predicting the motion of future frames from the initial frame according to an instruction, which has wide applications in virtual reality, robotics, and content creation. Previous TVP methods make…
Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substantial size of 3D MLLMs and the high dimensionality of input…
This paper presents PANTHER, a real-time perception-aware (PA) trajectory planner for multirotor-UAVs (Unmanned Aerial Vehicles) in dynamic environments. PANTHER plans trajectories that avoid dynamic obstacles while also keeping them in the…
Event sensing is a major component in bio-inspired flight guidance and control systems. We explore the usage of event cameras for predicting time-to-contact (TTC) with the surface during ventral landing. This is achieved by estimating…
Recently, we have witnessed the rise of novel ``event-based'' camera sensors for high-speed, low-power video capture. Rather than recording discrete image frames, these sensors output asynchronous ``event'' tuples with microsecond…
Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is…