10 accepted papers
We propose action-agnostic point-level (AAPL) supervision for temporal action detection to achieve accurate action instance detection with a lightly annotated dataset. In the proposed scheme, a small portion of video frames is sampled in an unsupervised manner and presented to human annotators, who…
Result diversification (RD) is a crucial technique in Text-to-Image Retrieval for enhancing the efficiency of a practical application. Conventional methods focus solely on increasing the diversity metric of image appearances. However, the diversity metric and its desired value vary depending on the
Human cognition is robust in estimating depth ordering and occluded regions of objects, including amodal instance segmentation (AIS). Object-centric representation learning (OCRL) is an unsupervised approach to obtaining a new representation that mimics human common sense, such as amodal perception.…
Deep learning for action recognition is an important technology for understanding videos. However, collecting video training dataset for deep learning model with low cost while maintaining enough diversity is challenging. In this paper, we propose a semi-automatic labeling framework for action recog…
Large-scale pre-trained models (PTMs) provide remarkable zero-shot classification capability covering a wide variety of object classes. However, practical applications do not always require the classification of all kinds of objects, and leaving the model capable of recognizing unnecessary classes n…
Echoes reflect a geometric structure of a scene surrounding a sound source. In this paper, we address the problem of estimating depth maps of indoor scenes based on echoes. First, we experimentally show that fusing multiple acoustic features, especially spectrogram and angular spectrum, can improve…
Many variants of unsupervised domain adaptation (UDA) problems have been proposed and solved individually. Its side effect is that a method that works for one variant is often ineffective for or not even applicable to another, which has prevented practical applications. In this paper, we give a gene…
Lifelong learning aims to train a highly expressive model for a new task while retaining all knowledge for previous tasks. However, many practical scenarios do not always require the system to remember all of the past knowledge. Instead, ethical considerations call for selective and proactive forget…
Although several powerful joint filters for cross-modal image pairs have been proposed, the existing joint filters generate severe artifacts when there are misalignments between a target and a guidance images. Our goal is to generate an artifact-free output image even from the misaligned target and…
This paper presents a novel unified gradient-domain image reconstruction framework with intensity-range constraint and base-structure constraint. The existing method for manipulating base structures and detailed textures are classifiable into two major approaches: i) gradient-domain and ii) layer-de…