Video-text retrieval, the task of retrieving videos based on a textual query or vice versa, is of paramount importance for video understanding and multimodal information retrieval. Recent methods in this area rely primarily on visual and textual features and often ignore audio, although it helps enhance overall comprehension of video content. Moreover, traditional models that incorporate audio blindly utilize the audio input regardless of whether it is useful or not, resulting in suboptimal video representation. To address these limitations, we propose a novel video-text retrieval framework, Audio-guided VIdeo representation learning with GATEd attention (AVIGATE), that effectively leverages audio cues through a gated attention mechanism that selectively filters out uninformative audio signals. In addition, we propose an adaptive margin-based contrastive loss to deal with the inherently unclear positive-negative relationship between video and text, which facilitates learning better video-text alignment. Our extensive experiments demonstrate that AVIGATE achieves state-of-the-art performance on all the public benchmarks.

Sound source localization (SSL) is the task of locating the source of sound within an image. Due to the lack of localization labels, the de facto standard in SSL has been to represent an image and audio as a single embedding vector each, and use them to learn SSL via contrastive learning. To this end, previous work samples one of local image features as the image embedding and aggregates all local audio features to obtain the audio embedding, which is far from optimal due to the presence of noise and background irrelevant to the actual target in the input. We present a novel SSL method that addresses this chronic issue by joint slot attention on image and audio. To be specific, two slots competitively attend image and audio features to decompose them into target and off-target representations, and only target representations of image and audio are used for contrastive learning. Also, we introduce cross-modal attention matching to further align local features of image and audio. Our method achieved the best in almost all settings on three public benchmarks for SSL, and substantially outperformed all the prior work in cross-modal retrieval.

Attribute-based person search is the task of finding person images that are best matched with a set of text attributes given as query. The main challenge of this task is the large modality gap between attributes and images. To reduce the gap, we present a new loss for learning cross-modal embeddings in the context of attribute-based person search. We regard a set of attributes as a category of people sharing the same traits. In a joint embedding space of the two modalities, our loss pulls images close to their person categories for modality alignment. More importantly, it pushes apart a pair of person categories by a margin determined adaptively by their semantic distance, where the distance metric is learned end-to-end so that the loss considers importance of each attribute when relating person categories. Our loss guided by the adaptive semantic margin leads to more discriminative and semantically well-arranged distributions of person images. As a consequence, it enables a simple embedding model to achieve state-of-the-art records on public benchmarks without bells and whistles.

This paper proposes a new method for person search, the task of detecting a specific person exemplified by a query image from a gallery of scene images. Current state-of-the-art techniques in person search demonstrate impressive performance, but are limited in terms of efficiency and scalability since they require multiple models and/or have to re-process gallery images per query. We argue that a concise framework with a single neural network can achieve both of scalability and performance at once. In our framework, the network detects people and extracts their appearance features so that person search is done by finding the person closest to the query in the feature space. For performance, we focus on the quality of the person appearance features: Our network is designed and trained to produce person features that are discriminative, fine-grained, adaptive to appearance variations, and robust against person localization errors. To this end, we design channel attention and part-wise spatial attention modules as well as a loss for learning discriminative features. Our framework outperforms current state of the art on the PRW benchmark even with the concise pipeline based on a single network.

Obstacle detection is one of the key requirements for autonomous vehicles. Many researchers have developed the techniques for obstacle detection for the safety of the drivers. Vision-based technique is one of popular obstacle detection techniques. We survey vision-based obstacle detection approaches, and present two approaches. In future work, we intend to implement a dynamic obstacle detection technique using vision sensors in urban road.

With an increased awareness of living a health-conscious lifestyle, many efforts are made to reduce stress levels. However, activities such as exercising require an action to go to a certain location and effort to set aside an allocated time. To effectively contribute towards lowering stress levels, we propose convenient, entertaining, and time-effective ways of relieving stress with objects that are used and seen inside home and workplaces. Relieving stress within daily routines can greatly contribute towards making home and workplace more enjoyable, saving time, and improving physical, emotional and psychological health. Specifically, we present: (1) a magic mirror, (2) an interactive media wall, (3) an interactive plant, and (4) an interactive living room wall. We deploy these in real-world environments to demonstrate how interactive objects can play an important role in home and workplaces.