Related papers: CLASP: Cross-modal Salient Anchor-based Semantic P…
Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal…
Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over long temporal windows. In this paper, we present SPELL, a…
Natural language video localization (NLVL) is a crucial task in video understanding that aims to localize the target moment in videos specified by a given language description. Recently, a point-supervised paradigm has been presented to…
Enabling computational systems with the ability to localize actions in video-based content has manifold applications. Traditionally, such a problem is approached in a fully-supervised setting where video-clips with complete frame-by-frame…
Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…
Audio-visual event localization (AVEL) plays a critical role in multimodal scene understanding. While existing datasets for AVEL predominantly comprise landscape-oriented long videos with clean and simple audio context, short videos have…
Multimodal semantic communication, which integrates various data modalities such as text, images, and audio, significantly enhances communication efficiency and reliability. It has broad application prospects in fields such as artificial…
Video saliency prediction is crucial for downstream applications, such as video compression and human-computer interaction. With the flourishing of multimodal learning, researchers started to explore multimodal video saliency prediction,…
The goal of weakly supervised video anomaly detection is to learn a detection model using only video-level labeled data. However, prior studies typically divide videos into fixed-length segments without considering the complexity or…
Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper…
Multimodal Entity Linking (MEL) aims to associate textual and visual mentions with entities in a multimodal knowledge graph. Despite its importance, current methods face challenges such as incomplete contextual information, coarse…
In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set…
We address the problem of active speaker detection through a new framework, called SPELL, that learns long-range multimodal graphs to encode the inter-modal relationship between audio and visual data. We cast active speaker detection as a…
In this paper, we present a gated convolutional neural network and a temporal attention-based localization method for audio classification, which won the 1st place in the large-scale weakly supervised sound event detection task of Detection…
Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the…
A good joint training framework is very helpful to improve the performances of weakly supervised audio tagging (AT) and acoustic event detection (AED) simultaneously. In this study, we propose three methods to improve the best…
Active learning aims to address the paucity of labeled data by finding the most informative samples. However, when applying to semantic segmentation, existing methods ignore the segmentation difficulty of different semantic areas, which…
Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies% at the frame level, which can be roughly interpreted as the binary or…
Audio-visual speech recognition (AVSR) aims to transcribe human speech using both audio and video modalities. In practical environments with noise-corrupted audio, the role of video information becomes crucial. However, prior works have…
The goal of Multilingual Visual Answer Localization (MVAL) is to locate a video segment that answers a given multilingual question. Existing methods either focus solely on visual modality or integrate visual and subtitle modalities.…