相关论文: MAN: Moment Alignment Network for Natural Language…
We propose a method for generating a temporally remapped video that matches the desired target duration while maximally preserving natural video dynamics. Our approach trains a neural network through self-supervision to recognize and…
In this paper, we propose a novel method for video moment retrieval (VMR) that achieves state of the arts (SOTA) performance on R@1 metrics and surpassing the SOTA on the high IoU metric (R@1, IoU=0.7). First, we propose to use a multi-head…
Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models. This work is motivated by the analysis of physiological time series data in electronic health…
Multi-person motion prediction is a complex and emerging field with significant real-world applications. Current state-of-the-art methods typically adopt dual-path networks to separately modeling spatial features and temporal features.…
Automatically describing a video with natural language is regarded as a fundamental challenge in computer vision. The problem nevertheless is not trivial especially when a video contains multiple events to be worthy of mention, which often…
Visual question answering by using information from multiple modalities has attracted more and more attention in recent years. However, it is a very challenging task, as the visual content and natural language have quite different…
Retrieving partially relevant segments from untrimmed videos remains difficult due to two persistent challenges: the mismatch in information density between text and video segments, and limited attention mechanisms that overlook semantic…
Person re-identification (person re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian…
Cooperative perception presents significant potential for enhancing the sensing capabilities of individual vehicles, however, inter-agent latency remains a critical challenge. Latencies cause misalignments in both spatial and semantic…
To retrieve more relevant, appropriate and useful documents given a query, finding clues about that query through the text is crucial. Recent deep learning models regard the task as a term-level matching problem, which seeks exact or…
Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by the advancement of representation learning techniques and inspiration of human behaviors.…
In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks…
Video Anomaly Detection (VAD), aiming to identify abnormalities within a specific context and timeframe, is crucial for intelligent Video Surveillance Systems. While recent deep learning-based VAD models have shown promising results by…
Video retrieval requires aligning visual content with corresponding natural language descriptions. In this paper, we introduce Modality Auxiliary Concepts for Video Retrieval (MAC-VR), a novel approach that leverages modality-specific tags…
In recent years, large language models have demonstrated remarkable capabilities in natural language understanding and generation. However, these models often struggle with hallucinations and maintaining long term contextual relevance,…
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the…
Long-context question answering over narrative tasks is challenging because correct answers often hinge on reconstructing a coherent timeline of events while preserving contextual f low in a limited context window. Retrievalaugmented…
Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras. It is a practical yet challenging task of how to embed spatial and temporal information of a video into its feature…
Despite the recent success of neural networks in image feature learning, a major problem in the video domain is the lack of sufficient labeled data for learning to model temporal information. In this paper, we propose an unsupervised…
Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of…