24 accepted papers
"Human trajectory prediction is typically posed as a zero-shot generalization problem: a predictor is learnt on a dataset of human motion in training scenes, and then deployed on unseen test scenes. While this paradigm has yielded tremendous progress, it fundamentally assumes that trends in human be…
Aligned text-image encoders such as CLIP have become the de-facto model for vision-language tasks. Furthermore modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment exist between uni-modal vision and language encoder…
Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning which is highly memory-intensive for tasks with high-resolution data e.g. video understanding small object detection and point cloud analysis…
Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of performance, many of them are in the low-data regime, making fine-tu…
Are multimodal inputs necessary for grammar induction? Recent work has shown that multimodal training inputs can improve grammar induction. However, these improvements are based on comparisons to weak text-only baselines that were trained on relatively little textual data. To determine whether multi…
We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this we define a common format "visual sentences" in which we can represent raw images and videos as well as annotated data sources such as semantic se…
Modern computer vision pipelines handle large images in one of two sub-optimal ways: down-sampling or cropping. These two methods incur significant losses in the amount of information and context present in an image. There are many downstream applications in which global context matters as much as h…
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…
We present RAFTformer, a real-time action forecasting transformer for latency aware real-world action forecasting applications. RAFTformer is a two-stage fully transformer based architecture which consists of a video transformer backbone that operates on high resolution, short range clips and a head…
Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content. Given limited GPU memory, training TAL end to end (i.e., from videos to predictions) on long videos is a significant challenge. Most methods can only train on pre-extracted fe…
The recent emergence of Large Language Models based on the Transformer architecture has enabled dramatic advancements in the field of Natural Language Processing. However, these models have long inference latency, which limits their deployment and makes them prohibitively expensive for various real-…
Recent action recognition models have achieved impressive results by integrating objects, their locations and interactions. However, obtaining dense structured annotations for each frame is tedious and time-consuming, making these methods expensive to train and less scalable. At the same time, if a…
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countri…
In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative positional embeddings and residual pooling connections. We instantia…
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without hitting the computation or memory bottlenecks. In this paper,…
Recently, video transformers have shown great success in video understanding, exceeding CNN performance; yet existing video transformer models do not explicitly model objects, although objects can be essential for recognizing actions. In this work, we present Object-Region Video Transformers (ORViT)…
We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory footprint from the depth of the model, Reversible Vision Transformers enable memory efficient scaling of transformer architectures. We adapt two popular models, name…
The recently proposed Conformer model has become the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture that captures both local and global features. However, through a series of systematic studies, we find that the Conformer architectu…
Human trajectory forecasting is an inherently multimodal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to the model, such as long term goals and (b) sources that are unknown to both the agent & the model, such as intent of oth…
Recent advances in trajectory prediction have shown that explicit reasoning about agents' intent is important to accurately forecast their motion. However, the current research activities are not directly applicable to intelligent and safety critical systems. This is mainly because very few public d…
We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dim…
Human trajectory forecasting with multiple socially interact-ing agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory pre…
Human movement is goal-directed and influenced by the spatial layout of the objects in the scene. To plan future human motion, it is crucial to perceive the environment -- imagine how hard it is to navigate a new room with lights off. Existing works on predicting human motion do not pay attention to…
We present a new task that predicts future locations of people observed in first-person videos. Consider a first-person video stream continuously recorded by a wearable camera. Given a short clip of a person that is extracted from the complete stream, we aim to predict that person's location in futu…