Related papers: Adaptique: Multi-objective and Context-aware Onlin…
Human vision is highly adaptive, efficiently sampling intricate environments by sequentially fixating on task-relevant regions. In contrast, prevailing machine vision models passively process entire scenes at once, resulting in excessive…
When we interact with small screen devices, sometimes we make errors, due to our abilities/disabilities, contextual factors that distract our attention or problems related to the interface. Recovering from these errors may be time consuming…
Computer vision algorithms are known to be extremely sensitive to the environmental conditions in which the data is captured, e.g., lighting conditions and target density. Tuning of parameters or choosing a completely new algorithm is often…
Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…
Adaptive control for real-time manipulation requires quick estimation and prediction of object properties. While robot learning in this area primarily focuses on using vision, many tasks cannot rely on vision due to object occlusion. Here,…
We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the classical prediction-with-expert-advice set-up, we consider…
Searching for and making decisions about information is becoming increasingly difficult as the amount of information and number of choices increases. Recommendation systems help users find items of interest of a particular type, such as…
Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and…
Object reorientation is a critical task for robotic grippers, especially when manipulating objects within constrained environments. The task poses significant challenges for motion planning due to the high-dimensional output actions with…
Choosing a decision threshold is one of the challenging job in any classification tasks. How much the model is accurate, if the deciding boundary is not picked up carefully, its entire performance would go in vain. On the other hand, for…
Moving target selection in multimedia interactive systems faces unprecedented challenges as users increasingly interact across diverse and dynamic contexts-from live streaming in moving vehicles to VR gaming in varying environments.…
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…
Ubiquitous information access becomes more and more important nowadays and research is aimed at making it adapted to users. Our work consists in applying machine learning techniques in order to adapt the information access provided by…
Image-to-video adaptation seeks to efficiently adapt image models for use in the video domain. Instead of finetuning the entire image backbone, many image-to-video adaptation paradigms use lightweight adapters for temporal modeling on top…
The dynamic environment in the real world calls for the adaptive techniques for information filtering, namely to provide real-time responses to the changes of system data. Where many incremental algorithms are designed for this purpose,…
When establishing a visual connection between a virtual reality user and an augmented reality user, it is important to consider whether the augmented reality user faces a surplus of information. Augmented reality, compared to virtual…
In the context of view-dependent point-cloud streaming in a scene, our rate allocation is "adaptive" in the sense that it priorities the point-cloud models depending on the camera view and the visibility of the objects and their distance as…
Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case…
Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces Adaptor library that transposes the traditional model-centric approach composed of…
Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deployment on resource-constrained edge devices. Object detection…