Related papers: BiC-Net: Learning Efficient Spatio-Temporal Relati…
This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial…
Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…
Video-Text Retrieval has been a hot research topic with the growth of multimedia data on the internet. Transformer for video-text learning has attracted increasing attention due to its promising performance. However, existing cross-modal…
Cross-modal retrieval has drawn much attention in both computer vision and natural language processing domains. With the development of convolutional and recurrent neural networks, the bottleneck of retrieval across image-text modalities is…
Learning common subspace is prevalent way in cross-modal retrieval to solve the problem of data from different modalities having inconsistent distributions and representations that cannot be directly compared. Previous cross-modal retrieval…
Temporal modeling in videos is a fundamental yet challenging problem in computer vision. In this paper, we propose a novel Temporal Bilinear (TB) model to capture the temporal pairwise feature interactions between adjacent frames. Compared…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
Many methods for learning from video sequences involve temporally processing 2D CNN features from the individual frames or directly utilizing 3D convolutions within high-performing 2D CNN architectures. The focus typically remains on how to…
Cross-modal (e.g. image-text, video-text) retrieval is an important task in information retrieval and multimodal vision-language understanding field. Temporal understanding makes video-text retrieval more challenging than image-text…
Multi-channel video-language retrieval require models to understand information from different channels (e.g. video$+$question, video$+$speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal…
We propose a novel method for real-time face alignment in videos based on a recurrent encoder-decoder network model. Our proposed model predicts 2D facial point heat maps regularized by both detection and regression loss, while uniquely…
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open…
In recent years, cross-modal retrieval has drawn much attention due to the rapid growth of multimodal data. It takes one type of data as the query to retrieve relevant data of another type. For example, a user can use a text to retrieve…
We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a…
Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared…
In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…
This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no…
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…
Abnormality detection in video poses particular challenges due to the infinite size of the class of all irregular objects and behaviors. Thus no (or by far not enough) abnormal training samples are available and we need to find…
Video-text retrieval (VTR) aims to locate relevant videos using natural language queries. Current methods, often based on pre-trained models like CLIP, are hindered by video's inherent redundancy and their reliance on coarse, final-layer…