45 accepted papers
Robotics has long sought to develop robots capable of completing previously unseen long-horizon tasks. Hierarchical approaches offer a pathway for achieving this goal by executing skill combinations arranged by a task planner, with each visuomotor skill pre-trained using a specific imitation learnin…
We present BASKET, a large-scale basketball video dataset for fine-grained skill estimation. BASKET contains 4,477 hours of video capturing 32,232 basketball players from all over the world. Compared to prior skill estimation datasets, our dataset includes a massive number of skilled participants wi…
Video Question Answering (VQA) in long videos poses the key challenge of extracting relevant information and modeling long-range dependencies from many redundant frames. The self-attention mechanism provides a general solution for sequence modeling, but it has a prohibitive cost when applied to a ma…
Robotics has long sought to develop robots capable of completing previously unseen long-horizon tasks. Hierarchical approaches offer a pathway for achieving this goal by executing skill combinations arranged by a task planner, with each visuomotor skill pre-trained using a specific imitation learnin
We present ExAct, a new video-language benchmark for expert-level understanding of skilled physical human activities. Our new benchmark contains 3,521 expert-curated video question-answer pairs spanning 11 physical activities in 6 domains: Sports, Bike Repair, Cooking, Health, Music, and Dance. ExAc…
Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm without dynamic feedback, limiting the model’s capacity to se…
Vision-language-action (VLA) models present a promising paradigm by training policies directly on real robot datasets like Open X-Embodiment. However, the high cost of real-world data collection hinders further data scaling, thereby restricting the generalizability of VLAs. In this paper, we introdu
Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are constrained by frame limitations, often losing essential temporal det…
Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and fine- tuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT) with extensive video data and long Chain-of-Thought (CoT) anno
Long-form video understanding has been a challenging task due to the high redundancy in video data and the abundance of query-irrelevant information. To tackle this challenge, we propose VideoTree, a training-free framework which builds a query-adaptive and hierarchical video representation for LLM…
"Goal-oriented planning, or anticipating a series of actions that transition an agent from its current state to a predefined objective, is crucial for developing intelligent assistants aiding users in daily procedural tasks. The problem presents significant challenges due to the need for comprehensi…
"We present , a 3D-aware diffusion model addressing the exo-to-ego viewpoint translation task — generating first-person (egocentric) view images from the corresponding third-person (exocentric) images. Building on the diffusion model’s ability to generate photorealistic images, we propose a transfor…
We present LLoVi, a simple yet effective **L**anguage-based **Lo**ng-range **Vi**deo question-answering (LVQA) framework. Our method decomposes the short- and long-range modeling aspects of LVQA into two stages. First, we use a short-term visual captioner to generate textual descriptions of short vi…
Robot Imitation Learning (IL) is a crucial technique in robot learning, where agents learn by mimicking human demonstrations. However, IL encounters scalability challenges stemming from both non-user-friendly demonstration collection methods and the extensive time required to amass a sufficient numb…
We present Ego-Exo4D a diverse large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g. sports music dance bike repair). 740 participants from 13 cities worldwide perform…
Active Speaker Detection (ASD) aims to identify who is speaking in each frame of a video. Solving ASD involves using audio and visual information in two complementary contexts: long-term intra-speaker context models the temporal dependencies of the same speaker while short-term inter-speaker context…
Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate fr…
"Locating specific moments within long videos (20–120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5–30 seconds) grounding methods to this problem yields poor performance. Since most real-life videos, such as those on YouTube and A…
"Traditional audio-visual methods rely on independent audio and visual backbones, which is costly and not scalable. In this work, we investigate using an audio-visual siamese network () for efficient and scalable audio-visual pretraining. Our framework uses a single shared vision transformer backbon…
Most video captioning models are designed to process short video clips of few seconds and output text describing low-level visual concepts (e.g. objects scenes atomic actions). However most real-world videos last for minutes or hours and have a complex hierarchical structure spanning different tempo…
The ability to distinguish between different movie scenes is critical for understanding the storyline of a movie. However, accurately detecting movie scenes is often challenging as it requires the ability to reason over very long movie segments. This is in contrast to most existing video recognition…
Click-based interactive image segmentation aims at extracting objects with a limited user clicking. A hierarchical backbone is the de-facto architecture for current methods. Recently, the plain, non-hierarchical Vision Transformer (ViT) has emerged as a competitive backbone for dense prediction task…
The canonical approach to video-text retrieval leverages a coarse-grained or fine-grained alignment between visual and textual information. However, retrieving the correct video according to the text query is often challenging as it requires the ability to reason about both high-level (scene) and lo…
The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks…
Vision transformers (ViTs) have achieved impressive results on various computer vision tasks in the last several years. In this work, we study the capability of frozen ViTs, pretrained only on visual data, to generalize to audio-visual data without finetuning any of its original parameters. To do so…
"We introduce an audiovisual method for long-range text-to-video retrieval. Unlike previous approaches designed for short video retrieval (e.g., 5-15 seconds in duration), our approach aims to retrieve minute-long videos that capture complex human actions. One challenge of standard video-only approa…
In this paper we consider the problem of classifying fine-grained, multi-step activities (e.g., cooking different recipes, making disparate home improvements, creating various forms of arts and crafts) from long videos spanning up to several minutes. Accurately categorizing these activities requires…
"Most modern video recognition models are designed to operate on short video clips (e.g., 5-10s in length). Thus, it is challenging to apply such models to long movie understanding tasks, which typically require sophisticated long-range temporal reasoning. The recently introduced video transformers…
Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on large-scale image datasets to achieve top performance. In this paper…
"Most modern approaches in temporal action localization divide this problem into two parts: (i) short-term feature extraction and (ii) long-range temporal boundary localization. Due to the high GPU memory cost caused by processing long untrimmed videos, many methods sacrifice the representational po…
We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named “TimeSformer,” adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches.…
We present Vx2Text, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a l…
Many objects in the real world undergo dramatic variations in visual appearance. For example, a tomato may be red or green, sliced or chopped, fresh or fried, liquid or solid. Training a single detector to accurately recognize tomatoes in all these different states is challenging. On the other hand,…
We introduce a method for simultaneously classifying, segmenting and tracking object instances in a video sequence. Our method, named MaskProp, adapts the popular Mask R-CNN to video by adding a mask propagation branch that propagates frame-level object instance masks from each video frame to all th…
Modern approaches for multi-person pose estimation in video require large amounts of dense annotations. However, labeling every frame in a video is costly and labor intensive. To reduce the need for dense annotations, we propose a PoseWarper network that leverages training videos with sparse annotat…
We present a model that uses a single first-person image to generate an egocentric basketball motion sequence in the form of a 12D camera configuration trajectory, which encodes a player's 3D location and 3D head orientation throughout the sequence. To do this, we first introduce a future convolutio…
We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent frames. This naturally renders the approach robust to occlu…
This paper presents a method to assess a basketball player's performance from his/her first-person video. A key challenge lies in the fact that the evaluation metric is highly subjective and specific to a particular evaluator. We leverage the first-person camera to address this challenge. The spatio…
Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with poor localization around the boundaries. Prior work has att…
Unlike traditional third-person cameras mounted on robots, a first-person camera, captures a person's visual sensorimotor object interactions from up close. In this paper, we study the tight interplay between our momentary visual attention and motor action with objects from a first-person camera. We…
Conditional random fields (CRFs) provide a powerful tool for structured prediction, but cast significant challenges in both the learning and inference steps. Approximation techniques are widely used in both steps, which should be considered jointly to guarantee good performance (a.k.a. “inferning").…
A first-person camera, placed at a person's head, captures, which objects are important to the camera wearer. Most prior methods for this task learn to detect such important objects from the manually labeled first-person data in a supervised fashion. However, important objects are strongly related t…
The state-of-the-art in semantic segmentation is currently represented by fully convolutional networks (FCNs). However, FCNs use large receptive fields and many pooling layers, both of which cause blurring and low spatial resolution in the deep layers. As a result FCNs tend to produce segmentations…
Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a higher-level task such as object detection. However, we claim that…
Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a boundary. Inspired by this observation, in this work we show how to…