Related papers: Bridging the Gap Between Object Detection and User…

Connecting multiple machine learning models into a pipeline is effective for handling complex problems. By breaking down the problem into steps, each tackled by a specific component model of the pipeline, the overall solution can be made…

Multi-objective reinforcement learning (MORL) allows a user to express preference over outcomes in terms of the relative importance of the objectives, but standard metrics cannot capture whether changes in preference reliably change the…

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the…

Human-robot collaboration requires robots to quickly infer user intent, provide transparent reasoning, and assist users in achieving their goals. Our recent work introduced GUIDER, our framework for inferring navigation and manipulation…

In exploratory search, users often submit vague queries to investigate unfamiliar topics, but receive limited feedback about how the search engine understood their input. This leads to a self-reinforcing cycle of mismatched results and…

Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing…

We consider the problem of composed image retrieval that takes an input query consisting of an image and a modification text indicating the desired changes to be made on the image and retrieves images that match these changes. Current…

This thesis contributes a structured inquiry into the open actuarial mathematics problem of modelling user behaviour using machine learning methods, in order to predict purchase intent of non-life insurance products. It is valuable for a…

Object-goal visual navigation requires robots to reason over semantic structure and act effectively under partial observability. Recent approaches based on object-level topological maps enable long-horizon navigation without dense geometric…

The robustness of object detection algorithms plays a prominent role in real-world applications, especially in uncontrolled environments due to distortions during image acquisition. It has been proven that the performance of object…

Multi-Object Tracking (MOT) aims to detect and associate all desired objects across frames. Most methods accomplish the task by explicitly or implicitly leveraging strong cues (i.e., spatial and appearance information), which exhibit…

The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning. In the recent culmination of unsupervised object-centric learning, the Slot-Attention module has…

Recommender systems take inputs from user history, use an internal ranking algorithm to generate results and possibly optimize this ranking based on feedback. However, often the recommender system is unaware of the actual intent of the user…

Previous object detectors make predictions based on dense grid points or numerous preset anchors. Most of these detectors are trained with one-to-many label assignment strategies. On the contrary, recent query-based object detectors depend…

Imitation learning for mobile manipulation is a key challenge in the field of robotic manipulation. However, current mobile manipulation frameworks typically decouple navigation and manipulation, executing manipulation only after reaching a…

Electric automation systems offer convenience and efficiency in controlling electrical circuits and devices. Traditionally, these systems rely on predefined commands for control, limiting flexibility and adaptability. In this paper, we…

In object recognition applications, object images usually appear with different quality levels. Practically, it is very important to indicate object image qualities for better application performance, e.g. filtering out low-quality object…

In interactive object segmentation a user collaborates with a computer vision model to segment an object. Recent works employ convolutional neural networks for this task: Given an image and a set of corrections made by the user as input,…

This work addresses the task of weakly-supervised object localization. The goal is to learn object localization using only image-level class labels, which are much easier to obtain compared to bounding box annotations. This task is…

Video-based computer vision tasks can benefit from estimation of the salient regions and interactions between those regions. Traditionally, this has been done by identifying the object regions in the images by utilizing pre-trained models…