89 accepted papers
Optimization‐based text‑to‑3D methods distill guidance from 2D generative models via Score Distillation Sampling (SDS), but implicitly treat this guidance as static. This work shows that ignoring source dynamics yields inconsistent trajectories that suppress or merge semantic cues, leading to "seman
Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded streams. Secondly, due to the high cost of collecting and tra…
We present the first systematic analysis of multimodal large language models (MLLMs) in personalized question-answering requiring ego-grounding - the ability to understand the camera-wearer in egocentric videos. To this end, we introduce MyEgo, the first egocentric VideoQA dataset designed to evalua
Recovering global human and camera motion from monocular video is essential for world-coordinate human reconstruction but remains challenging due to entangled motions in image space. Traditional SLAM methods estimate monocular camera motion but fail in scenes dominated by foreground objects such as
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redunda…
Textured 3D morphing seeks to generate smooth and plausible transitions between two 3D assets, preserving both structural coherence and fine-grained appearance. This ability is crucial not only for advancing 3D generation research but also for practical applications in animation, editing, and digita…
We introduce UCS-Bench, a dataset spanning 170+ hours of egocentric visual observations with 7K+ timestamped questions for diagnosing User-centric Continual Spatial intelligence in egocentric video streams. UCS-Bench targets a new problem that emphasizes dynamic spatial reasoning, long-term memory, …
Learning-based structure-from-motion methods such as ACE-Zero have demonstrated strong performance in estimating camera poses and scene coordinates from unordered image collections without requiring ground truth supervision. However, the lack of global and multi-view consistency constraints in ACE-Z
Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-modal attention with quadratic computational cost, limiting their suitability for resource efficient deployment. Most efficiency oriented methods focu…
Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores the Key-Value (KV) of the historical tokens via LLM prefill and enables more efficient streaming QA. However, existing methods cache every one or t
Multimodal Large Language Models (MLLMs) have advanced open-world action understanding and can be adapted as generative classifiers for closed-set settings by autoregressively generating action labels as text. However, this approach is inefficient, and shared subwords across action labels introduce…
Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize *text-driven amodal 3D generation*, where text prompts steer the completion of unseen regions while strictly preser…
Pre-defined 3D object templates are widely used in 3D reconstruction of hand-object interactions. However, they often require substantial manual efforts to capture or source, and inherently restrict the adaptability of models to unconstrained interaction scenarios, e.g., heavily-occluded objects. To…
Training-free image editing with large diffusion models has become practical, yet faithfully performing complex non-rigid edits (e.g., pose or shape changes) remains highly challenging. We identify a key underlying cause: attention collapse in existing attention sharing mechanisms, where either posi
Autoregressive (AR) visual generation relies on tokenizers to map images to and from discrete sequences. However, tokenizers are trained to reconstruct clean images from ground-truth tokens, while AR generators are optimized only for token likelihood. This misalignment leads to generated token seque
Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and rasterization ordering. In this work, we identify a core bottle…
3D Gaussian Splatting (3DGS) is a powerful reconstruction technique; however, it requires initialization from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM) algorithms; however, SfM is time-consuming and restricts the app…
Recent synthetic 3D human datasets for the face, body, and hands have pushed the limits on photorealism. Face recognition and body pose estimation have achieved state-of-the-art performance using synthetic training data alone, but for the hand, there is still a large synthetic-to-real gap. This pape…
This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to condense data into compact latent codes with significant storag…
Online Action Detection (OAD) detects actions in streaming videos using past observations. State-of-the-art OAD approaches model past observations and their interactions with an anticipated future. The past is encoded using short- and long-term memories to capture immediate and long-range dependenci…
This work questions a common assumption of OOD detection, that models with higher in-distribution (ID) accuracy tend to have better OOD performance. Recent findings show this assumption doesn't always hold. A direct observation is that the later version of torchvision models improves ID accuracy but…
We present EgoBlind, the first egocentric VideoQA dataset collected from blind individuals to evaluate the assistive capabilities of contemporary multimodal large language models (MLLMs). EgoBlind comprises 1,392 first-person videos from the daily lives of blind and visually impaired individuals. It…
We introduce EgoTextVQA, a novel and rigorously constructed benchmark for egocentric QA assistance involving scene text. EgoTextVQA contains 1.5K ego-view videos and 7K scene-text aware questions that reflect real user needs in outdoor driving and indoor house-keeping activities. The questions are d…
Spurious correlations often arise when models associate features strongly correlated with, but not causally related to, the label e.g. an image classifier associates bodies of water with ducks. To mitigate spurious correlations, existing methods focus on learning unbiased representation or incorpora…
Vision Transformers (ViT) are remarkable at 3D pose estimation, yet they still encounter certain challenges. One issue is that the popular ViT architecture for pose estimation is limited to images and lacks temporal information. Another challenge is that the prediction often fails to maintain pixel…
View-Guided Point Cloud Completion (VG-PCC) aims to reconstruct complete point clouds from partial inputs by referencing single-view images. While existing VG-PCC models perform well on in-class predictions, they exhibit significant performance drops when generalizing to unseen categories. We identi…
Accurate camera motion estimation is essential for recovering global human motion in world coordinates from RGB video inputs. While SLAM is widely used for estimating camera trajectory and point cloud, monocular SLAM does so only up to an unknown scale factor. Previous works estimate the scale facto…
For deep regression, preserving the ordinality of the targets with respect to the feature representation improves performance across various tasks. However, a theoretical explanation for the benefits of ordinality is still lacking. This work reveals that preserving ordinality reduces the conditional…
Language-guided Affordance Segmentation (LASO) aims to identify actionable object regions based on text instructions. At the core of its practicality is learning generalizable affordance knowledge that captures functional regions across diverse objects. However, current LASO solutions struggle to ex…
Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of…
This work highlights a semantics misalignment in 3D human pose estimation. For the task of test-time adaptation, the misalignment manifests as overly smoothed and unguided predictions. The smoothing settles predictions towards some average pose. Furthermore, when there are occlusions or truncations,…
Standard 3D Gaussian Splatting (3DGS) relies on known or pre-computed camera poses and a sparse point cloud, obtained from structure-from-motion (SfM) preprocessing, to initialize and grow 3D Gaussians. We propose a novel SfM-Free 3DGS (SFGS) method for video input, eliminating the need for known ca…
We introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens -- verbalized text tokens, which provide compressed textual summaries of long-term observations, and visual tokens, encoded…
Given a textual query along with a corresponding video, the objective of moment retrieval aims to localize the moments relevant to the query within the video. While commendable results have been demonstrated by existing transformer-based approaches, predicting the accurate temporal span of the targe…
Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object queries. In applications such as AI assistants, the perspective shifts -- inputs are egocentric, and objects may be referred to implicitly through needs a…
Conditional diffusion models can create unseen images in various settings, aiding image interpolation. Interpolation in latent spaces is well-studied, but interpolation with specific conditions like text or image is less understood. Common approaches interpolate linearly in the conditioning space bu…
"We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic understanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation. Accurately reconstructing such interactions in is c…
We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video- language understanding. Specifically by forcing vision- language models (VLMs) to answer questions and simultane- ously provide visual evidence we seek to ascertain the extent to whic…
Data replay is a successful incremental learning technique for images. It prevents catastrophic forgetting by keeping a reservoir of previous data original or synthesized to ensure the model retains past knowledge while adapting to novel concepts. However its application in the video domain is rudim…
Regression tasks in computer vision such as age estimation or counting are often formulated into classification by quantizing the target space into classes. Yet real-world data is often imbalanced -- the majority of training samples lie in a head range of target values while a minority of samples sp…
Most works studying representation learning focus only on classification and neglect regression. Yet, the learning objectives and, therefore, the representation topologies of the two tasks are fundamentally different: classification targets class separation, leading to disconnected representations,…
In video super-resolution it is common to use a frame-wise alignment to support the propagation of information over time. The role of alignment is well-studied for low-level enhancement in video but existing works overlook a critical step -- resampling. We show through extensive experiments that for…
2D keypoints are commonly used as an additional cue to refine estimated 3D human meshes. Current methods optimize the pose and shape parameters with a reprojection loss on the provided 2D keypoints. Such an approach while simple and intuitive has limited effectiveness because the optimal solution is…
"Procedural activity videos often exhibit a long-tailed action distribution due to varying action frequencies and durations. However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail actions. Existing long-tail methods make class-independent ass…
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks yet they often struggle with reliable uncertainty quantification -a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are equipped for uncertainty estimation but cannot scale to large DNNs…
"Modeling the physical contacts between the hand and object is standard for refining inaccurate hand poses and generating novel human grasp in 3D hand-object reconstruction. However, existing methods rely on geometric constraints that cannot be specified or controlled. This paper introduces a novel…
2D human pose estimation predicts keypoint locations and the corresponding confidence. Calibration-wise, the confidence should be aligned with the pose accuracy. Yet existing pose estimation methods tend to estimate confidence with heuristics such as the maximum value of heatmaps. This work shows, t…
Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context information in an online setting remains an under-explored pr…
"Standard single-image super-resolution creates paired training data from high-resolution images through fixed downsampling kernels. However, real-world super-resolution (RWSR) faces unknown degradations in the low-resolution inputs, all the while lacking paired training data. Existing methods appro…
"In real-world video super-resolution (VSR), videos suffer from in-the-wild degradations and artifacts. VSR methods, especially recurrent ones, tend to propagate artifacts over time in the real-world setting and are more vulnerable than image super-resolution. This paper investigates the influence o…
Activation shaping has proven highly effective for identifying out-of-distribution (OOD) samples post-hoc. Activation shaping prunes and scales network activations before estimating the OOD energy score; such an extremely simple approach achieves state-of-the-art OOD detection with minimal in-distri…
"Text-driven video editing has emerged as a prominent application based on the breakthroughs of image diffusion models. Existing state-of-the-art methods focus on zero-shot frameworks due to limited training data and computing resources. To preserve structure consistency, previous frameworks usually…
We present Pose Integrated Gradient (PoseIG), the first interpretability technique designed for pose estimation. We extend the concept of integrated gradients for pose estimation to generate pixel-level attribution maps. To enable comparison across different pose frameworks, we unify different pose…
Recent advances in hand pose estimation have shed light on utilizing synthetic data to train neural networks, which however inevitably hinders generalization to real-world data due to domain gaps. To solve this problem, we present a framework for cross-domain semi-supervised hand pose estimation and…
A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this footprint - Dropping Intermediate Tensors (DropIT). DropIT drops mi…
In computer vision, it is often observed that formulating regression problems as a classification task yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the cross-entropy loss, outperforms regression with a mean squared error…
For monocular RGB-based 3D pose and shape estimation, multiple solutions are often feasible due to factors like occlusion and truncation. This work presents a multi-hypothesis probabilistic framework by optimizing the Kullback-Leibler divergence (KLD) between the data and model distribution. Our for…
Human actions in egocentric videos often feature hand-object interactions composed of a verb (performed by the hand) applied to an object. Despite their extensive scaling up, egocentric datasets still face two limitations — sparsity of action compositions and a closed set of interacting objects. Thi…
Direct mesh fitting for 3D hand shape reconstruction estimates highly accurate meshes. However, the resulting meshes are prone to artifacts and do not appear as plausible hand shapes. Conversely, parametric models like MANO ensure plausible hand shapes but are not as accurate as the non-parametric m…
Pose estimation is remarkably successful under supervised learning, but obtaining annotations, especially for new deployments, is costly and time-consuming. This work tackles adapting models trained on synthetic data to real-world target domains with only unlabelled data. A common approach is model…
"In temporal action segmentation, Timestamp supervision requires only a handful of labeled frames per video sequence. For unlabelled frames, Timestamp works rely on assigning hard labels and performance rapidly collapses under subtle violations of the annotation assumptions. We propose a novel Expec…
We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream. Specifically, we propose a motion vector-based warping method for propagating segmentation masks from ke…
Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles. Participants work without fixed instructions, and the sequences feature rich and natural variations in action ordering, mistakes, and corrections. Assembly101…
Video anomaly detection aims to automatically identify unusual objects or behaviours by learning from normal videos. Previous methods tend to use simplistic reconstruction or prediction constraints, which leads to the insufficiency of learned representations for normal data. As such, we propose a no…
"Local counts, or the number of objects in a local area, is a continuous value by nature. Yet recent state-of-the-art methods show that formulating counting as a classification task performs better than regression. Through a series of experiments on carefully controlled synthetic data, we show that…
Integral pose regression combines an implicit heatmap with end-to-end training for human body and hand pose estimation. Unlike detection-based heatmap methods, which decode final joint positions from the heatmap with a non-differentiable argmax operation, integral regression methods apply a differen…
Temporal action segmentation classifies the action of each frame in (long) video sequences. Due to the high cost of frame-wise labeling, we propose the first semi-supervised method for temporal action segmentation. Our method hinges on unsupervised representation learning, which, for temporal action…
"We present a semi-supervised learning approach to the temporal action segmentation task. The goal of the task is to temporally detect and segment actions in long, untrimmed procedural videos, where only a small set of videos are densely labelled, and a large collection of videos are unlabelled. To…
Video deblurring has achieved remarkable progress thanks to the success of deep neural networks. Most methods solve for the deblurring end-to-end with limited information propagation from the video sequence. However, different frame regions exhibit different characteristics and should be provided wi…
"In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that successfully balance the trade-off rely on fusing results from separa…
We propose a novel approach to generate temporally coherent UV coordinates for loose clothing. Our method is not constrained by human body outlines and can capture loose garments and hair. We implemented a differentiable pipeline to learn UV mapping between a sequence of RGB inputs and textures via…
Video question answering requires the models to understand and reason about both the complex video and language data to correctly derive the answers. Existing efforts have been focused on designing sophisticated cross-modal interactions to fuse the information from two modalities, while encoding the…
We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks targeting at causal action reasoning, temporal action reaso…
Heatmap-based detection methods are dominant for 2D human pose estimation even though regression is more intuitive. The introduction of the integral regression method, which, architecture-wise uses an implicit heatmap, brings the two approaches even closer together. This begs the question -- does de…
We present SemiHand, a semi-supervised framework for 3D hand pose estimation from monocular images. We pre-train the model on labelled synthetic data and fine-tune it on unlabelled real-world data by pseudo-labeling with consistency training. By design, we introduce data augmentation of differing di…
Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead significantly restricts their practical deployments on resource-limited devices. In this paper, we proposed a novel con…
We aim to recover the dense 3D surface of the hand from depth maps and propose a network that can predict mesh vertices, transformation matrices for every joint and joint coordinates in a single forward pass. Use fully convolutional architectures, we first map depth image features to the mesh grid a…
Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction","We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy of state-of-the-art metho…
Future prediction, especially in long-range videos, requires reasoning from current and past observations. In this work, we address questions of temporal extent, scaling, and level of semantic abstraction with a flexible multi-granular temporal aggregation framework. We show that it is possible to a…
Hand pose estimation from monocular RGB inputs is a highly challenging task. Many previous works for monocular settings only used RGB information for training despite the availability of corresponding data in other modalities such as depth maps. In this work, we propose to learn a joint latent repre…
In interactive instance segmentation, users give feedback to iteratively refine segmentation masks. The user-provided clicks are transformed into guidance maps which provide the network with necessary cues on the whereabouts of the object of interest. Guidance maps used in current systems are purely…
Hand image synthesis and pose estimation from RGB images are both highly challenging tasks due to the large discrepancy between factors of variation ranging from image background content to camera viewpoint. To better analyze these factors of variation, we propose the use of disentangled representat…
We present a self-supervision method for 3D hand pose estimation from depth maps. We begin with a neural network initialized with synthesized data and fine-tune it on real but unlabelled depth maps by minimizing a set of data-fitting terms. By approximating the hand surface with a set of spheres, we…
How can we teach a robot to predict what will happen next for an activity it has never seen before? We address the problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to the visual dom…
Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures. RNNs, widely used to process time series and sequence information, could greatly benefit from complex representations. We present a novel complex gated rec…
We present a simple and effective method for 3D hand pose estimation from a single depth frame. As opposed to previous state-of-arts based on holistic 3D regression, our method works on dense pixel-wise estimation. This is achieved by careful design choices in pose parameterization, which leverages…
This paper presents a new method for unsupervised segmentation of complex activities from video into multiple steps, or sub-activities, without any textual input. We propose an iterative discriminative-generative approach which alternates between discriminatively learning the appearance of sub-activ…
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-st…
State-of-the-art methods for 3D hand pose estimation from depth images require large amounts of annotated training data. We propose modelling the statistical relationship of 3D hand poses and corresponding depth images using two deep generative models with a shared latent space. By design, our archi…