相关论文: Looking for a better fit? An Incremental Learning …
The thesis contributes in several important ways to the research area of 3D object category learning and recognition. To cope with the mentioned limitations, we look at human cognition, in particular at the fact that human beings learn to…
Humans leverage multiple sensor modalities when interacting with objects and discovering their intrinsic properties. Using the visual modality alone is insufficient for deriving intuition behind object properties (e.g., which of two boxes…
Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes to additionally detect objects of new classes, in the absence…
Existing visual trackers mainly operate in a non-interactive, fire-and-forget manner, making them impractical for real-world scenarios that require human-in-the-loop adaptation. To overcome this limitation, we introduce Interactive…
The interaction between a vehicle navigation system and the driver of the vehicle can be formulated as a model-based reinforcement learning problem, where the navigation systems (agent) must quickly adapt to the characteristics of the…
Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a…
Conventional end-to-end autonomous driving methods often rely on explicit global scene representations, which typically consist of 3D object detection, online mapping, and motion prediction. In contrast, human drivers selectively attend to…
AI alignment is growing in importance, yet many current approaches learn safety behavior by directly modifying policy parameters, entangling normative constraints with the underlying policy. This often yields opaque, difficult-to-edit…
The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However,…
Egocentric hand-object motion generation is crucial for immersive AR/VR and robotic imitation but remains challenging due to unstable viewpoints, self-occlusions, perspective distortion, and noisy ego-motion. Existing methods rely on…
In this paper, we study Interaction-Grounded Learning (IGL) [Xie et al., 2021], a paradigm designed for realistic scenarios where the learner receives indirect feedback generated by an unknown mechanism, rather than explicit numerical…
Personalized motion planning holds significant importance within urban automated driving, catering to the unique requirements of individual users. Nevertheless, prior endeavors have frequently encountered difficulties in simultaneously…
Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might…
Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential…
Sequential recommendation demonstrates the capability to recommend items by modeling the sequential behavior of users. Traditional methods typically treat users as sequences of items, overlooking the collaborative relationships among them.…
In the realm of education, both independent learning and group learning are esteemed as the most classic paradigms. The former allows learners to self-direct their studies, while the latter is typically characterized by teacher-directed…
One fundamental task of multimodal models is to translate referred image regions to human preferred language descriptions. Existing methods, however, ignore the resolution adaptability needs of different tasks, which hinders them to find…
We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…
IMU-based gesture interfaces are being increasingly adopted as efficient, accessible, and intuitive alternatives to traditional input methods, such as touchscreens and voice. However, current gesture recognition algorithms are tailored to…
Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments, since the total number of objects and their…