Related papers: Semantic Audio-Visual Navigation
Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of…
Learning from audio-visual data offers many possibilities to express correspondence between the audio and visual content, similar to the human perception that relates aural and visual information. In this work, we present a method for…
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question…
Navigating to out-of-sight targets from human instructions in unfamiliar environments is a core capability for service robots. Despite substantial progress, most approaches underutilize reusable, persistent memory, constraining performance…
We deal with the navigation problem where the agent follows natural language instructions while observing the environment. Focusing on language understanding, we show the importance of spatial semantics in grounding navigation instructions…
Object goal navigation (ObjectNav) is a fundamental task in embodied AI, requiring an agent to locate a target object in previously unseen environments. This task is particularly challenging because it requires both perceptual and cognitive…
Exploration is one of the core challenges in reinforcement learning. A common formulation of curiosity-driven exploration uses the difference between the real future and the future predicted by a learned model. However, predicting the…
In this paper, we introduce a novel audio-visual multi-modal bridging framework that can utilize both audio and visual information, even with uni-modal inputs. We exploit a memory network that stores source (i.e., visual) and target (i.e.,…
Mobile robots exploring indoor environments increasingly rely on vision-language models to perceive high-level semantic cues in camera images, such as object categories. Such models offer the potential to substantially advance robot…
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…
We tackle the task of environmental event classification by drawing inspiration from the transformer neural network architecture used in machine translation. We modify this attention-based feedforward structure in such a way that allows the…
Audio and visual modalities are inherently connected in speech signals: lip movements and facial expressions are correlated with speech sounds. This motivates studies that incorporate the visual modality to enhance an acoustic speech signal…
We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates…
Accurately localizing audible objects based on audio-visual cues is the core objective of audio-visual segmentation. Most previous methods emphasize spatial or temporal multi-modal modeling, yet overlook challenges from ambiguous…
Humans can easily perceive the direction of sound sources in a visual scene, termed sound source localization. Recent studies on learning-based sound source localization have mainly explored the problem from a localization perspective.…
Navigating to a designated goal using visual information is a fundamental capability for intelligent robots. To address the practical demands of multi-modal, open-vocabulary goal queries and multi-goal visual navigation, we propose LagMemo,…
Although several research works have been reported on audio-visual sound source localization in unconstrained videos, no datasets and metrics have been proposed in the literature to quantitatively evaluate its performance. Defining the…
Objects produce different sounds when hit, and humans can intuitively infer how an object might sound based on its appearance and material properties. Inspired by this intuition, we propose Visual Acoustic Fields, a framework that bridges…
Open-vocabulary Object Goal Navigation requires an embodied agent to reach objects described by free-form language, including categories never seen during training. Existing end-to-end policies overfit small simulator datasets, achieving…
Target speech separation refers to extracting the target speaker's speech from mixed signals. Despite the recent advances in deep learning based close-talk speech separation, the applications to real-world are still an open issue. Two main…