Related papers: VATT: Transformers for Multimodal Self-Supervised …

The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic makes it well-suited for generating spatiotemporal tokens…

Recent advances of Transformers have brought new trust to computer vision tasks. However, on small dataset, Transformers is hard to train and has lower performance than convolutional neural networks. We make vision transformers as…

The real-world data tends to be heavily imbalanced and severely skew the data-driven deep neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task. Existing LTR methods seldom train Vision Transformers (ViTs)…

Recently, Transformers have been introduced into the field of acoustics recognition. They are pre-trained on large-scale datasets using methods such as supervised learning and semi-supervised learning, demonstrating robust generality--It…

Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the…

Deep learning has brought significant improvements to the field of cross-modal representation learning. For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained…

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models…

Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…

Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a…

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400)…

Vision Transformers (ViT) have recently emerged as a powerful alternative to convolutional networks (CNNs). Although hybrid models attempt to bridge the gap between these two architectures, the self-attention layers they rely on induce a…

Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks.…

This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video Transformer (MM-ViT), for video action recognition. Different from other schemes which solely utilize the decoded RGB frames, MM-ViT operates exclusively in…

Annotating 3D data remains a costly bottleneck for 3D object detection, motivating the development of weakly supervised annotation methods that rely on more accessible 2D box annotations. However, relying solely on 2D boxes introduces…

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn…

Video Object Segmentation (VOS) has emerged as an increasingly important problem with availability of larger datasets and more complex and realistic settings, which involve long videos with global motion (e.g, in egocentric settings),…

In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses…

The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as an efficient and effective alternative to full fine-tuning…

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…