21 accepted papers
We introduce Perception Encoder-Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Building on PE, PE-AV makes several key contributions to extend representations to audio, and natively support joint embeddings across audio-video,
We introduce Perception Encoder (PE), a family of state-of-the-art vision encoders for image and video understanding. Traditionally, vision encoders have relied on a variety of pretraining objectives, each excelling at different downstream tasks. Surprisingly, after scaling a carefully tuned image p…
Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark…
This paper focuses on creating synthetic data to improve the quality of image captions. Existing works typically have two shortcomings. First, they caption images from scratch, ignoring existing alt-text metadata, and second, lack transparency if the captioners’ training data (e.g. GPT) is unknown.…
Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative models. We believe that the main ingredient to the success of CLIP is its \textit{data} and \textit{not} the \textit{model}…
The success of contrastive language-image pretraining (CLIP) relies on the supervision from the pairing between images and captions which tends to be noisy in web-crawled data. We present Mixture of Data Experts (MoDE) and learn a system of CLIP data experts via clustering. Each data expert is train…
"Speech sounds convey a great deal of information about the scenes, resulting in a variety of effects ranging from reverberation to additional ambient sounds. In this paper, we manipulate input speech to sound as though it was recorded within a different scene, given an audio-visual conditional exam…
We introduce VoiceCraft, a token infilling neural codec language model, that achieves state-of-the-art performance on both speech editing and zero-shot text-to-speech (TTS) on audiobooks, internet videos, and podcasts. VoiceCraft employs a Transformer decoder architecture and introduces a token rear…
Large vision-language models are generally applicable to many downstream tasks, but come at an exorbitant training cost that only large institutions can afford. This paper trades generality for efficiency and presents Curation in Training (CiT), a simple and efficient vision-text learning algorithm…
There has been a longstanding belief that generation can facilitate a true understanding of visual data. In line with this, we revisit generatively pre-training visual representations in light of recent interest in denoising diffusion models. While directly pre-training with diffusion models does no…
Short-form video hashtag recommendation (SVHR) aims to recommend hashtags to content creators from videos and corresponding descriptions. Most prior studies regard SVHR as a classification or ranking problem and select hashtags from a set of limited candidates. However, in reality, users can create…
Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to effective accuracies and attractive FLOP counts, the added complexity actually makes these transformers slower than their vani…
We present Masked Audio-Video Learners (MAViL) to learn audio-visual representations with three complementary forms of self-supervision: (1) reconstructing masked raw audio and video inputs, (2) intra-modal and inter-modal contrastive learning with masking, and (3) self-training to predict aligned a…
We study the problem of human action recognition using motion capture (MoCap) sequences. Unlike existing techniques that take multiple manual steps to derive standardized skeleton representations as model input, we propose a novel Spatial-Temporal Mesh Transformer (STMT) to directly model the mesh s…
This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only th…
As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions related to multimodal learning through the lens of adversarial…
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextual multilingual multimodal embeddings. Under a zero-shot setting, we empirically demonstrate that perfo…
The quality of the image representations obtained from self-supervised learning depends strongly on the type of data augmentations used in the learning formulation. Recent papers have ported these methods from still images to videos and found that leveraging both audio and video signals yields stron…
The dominant paradigm for learning video-text representations – noise contrastive learning – increases the similarity of the representations of pairs of samples that are known to be related, such as text and video from the same sample, and pushes away the representations of all other pairs. We posit…
We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives fr…
We aim to search for a target person from a gallery of whole scene images for which the annotations of pedestrian bounding boxes are unavailable. Previous approaches to this problem have relied on a pedestrian proposal net, which may generate redundant proposals and increase the computational burden…