44 citations · 190 across the 27 of their papers we have counts for
29 papers · 1 filter
Interactive Episodic Memory with User Feedback
Nikesh Subedi, Loris Bazzani, Ziad Al-Halah
In episodic memory with natural language queries (EM-NLQ), a user may ask a question (e.g., "Where did I place the mug?") that requires searching a long egocentric video, captured…
Materialistic RIR: Material Conditioned Realistic RIR Generation
Mahnoor Fatima Saad, Sagnik Majumder, Kristen Grauman +1
Rings like gold, thuds like wood! The sound we hear in a scene is shaped not only by the spatial layout of the environment but also by the materials of the objects and surfaces wit…
MistExit: Learning to Exit for Early Mistake Detection in Procedural Videos
Sagnik Majumder, Anish Nethi, Ziad Al-Halah +1
We introduce the task of early mistake detection in video, where the goal is to determine whether a keystep in a procedural activity is performed correctly while observing as littl…
How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes
Mahnoor Fatima Saad, Ziad Al-Halah
How would the sound in a studio change with a carpeted floor and acoustic tiles on the walls? We introduce the task of material-controlled acoustic profile generation, where, given…
Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos
Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah +1
We introduce SWITCH-A-VIEW, a model that learns to automatically select the viewpoint to display at each timepoint when creating a how-to video. The key insight of our approach is…
Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah +2
Given a multi-view video, which viewpoint is most informative for a human observer? Existing methods rely on heuristics or expensive "best-view" supervision to answer this question…
Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos
Sagnik Majumder, Ziad Al-Halah, Kristen Grauman
We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framewor…
SpotEM: Efficient Video Search for Episodic Memory
Santhosh Kumar Ramakrishnan, Ziad Al-Halah, Kristen Grauman
The goal in episodic memory (EM) is to search a long egocentric video to answer a natural language query (e.g., "where did I leave my purse?"). Existing EM methods exhaustively ext…
NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory
Santhosh Kumar Ramakrishnan, Ziad Al-Halah, Kristen Grauman
Searching long egocentric videos with natural language queries (NLQ) has compelling applications in augmented reality and robotics, where a fluid index into everything that a perso…
Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation
Ziad Al-Halah, Santhosh K. Ramakrishnan, Kristen Grauman
In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environm…
Active Audio-Visual Separation of Dynamic Sound Sources
Sagnik Majumder, Kristen Grauman
We explore active audio-visual separation for dynamic sound sources, where an embodied agent moves intelligently in a 3D environment to continuously isolate the time-varying audio…
PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning
Santhosh Kumar Ramakrishnan, Devendra Singh Chaplot, Ziad Al-Halah +2
State-of-the-art approaches to ObjectGoal navigation rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Pote…
Move2Hear: Active Audio-Visual Source Separation
Sagnik Majumder, Ziad Al-Halah, Kristen Grauman
We introduce the active audio-visual source separation problem, where an agent must move intelligently in order to better isolate the sounds coming from an object of interest in it…
Environment Predictive Coding for Embodied Agents
Santhosh K. Ramakrishnan, Tushar Nagarajan, Ziad Al-Halah +1
We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised…
Semantic Audio-Visual Navigation
Changan Chen, Ziad Al-Halah, Kristen Grauman
Recent work on audio-visual navigation assumes a constantly-sounding target and restricts the role of audio to signaling the target's position. We introduce semantic audio-visual n…
Modeling Fashion Influence from Photos
Ziad Al-Halah, Kristen Grauman
The evolution of clothing styles and their migration across the world is intriguing, yet difficult to describe quantitatively. We propose to discover and quantify fashion influence…
Occupancy Anticipation for Efficient Exploration and Navigation
Santhosh K. Ramakrishnan, Ziad Al-Halah, Kristen Grauman
State-of-the-art navigation methods leverage a spatial memory to generalize to new environments, but their occupancy maps are limited to capturing the geometric structures directly…
Learning to Set Waypoints for Audio-Visual Navigation
Changan Chen, Sagnik Majumder, Ziad Al-Halah +3
In audio-visual navigation, an agent intelligently travels through a complex, unmapped 3D environment using both sights and sounds to find a sound source (e.g., a phone ringing in…
VisualEchoes: Spatial Image Representation Learning through Echolocation
Ruohan Gao, Changan Chen, Ziad Al-Halah +2
Several animal species (e.g., bats, dolphins, and whales) and even visually impaired humans have the remarkable ability to perform echolocation: a biological sonar used to perceive…
From Paris to Berlin: Discovering Fashion Style Influences Around the World
Ziad Al-Halah, Kristen Grauman
The evolution of clothing styles and their migration across the world is intriguing, yet difficult to describe quantitatively. We propose to discover and quantify fashion influence…
SoundSpaces: Audio-Visual Navigation in 3D Environments
Changan Chen, Unnat Jain, Carl Schissler +5
Moving around in the world is naturally a multisensory experience, but today's embodied agents are deaf---restricted to solely their visual perception of the environment. We introd…
Smile, Be Happy :) Emoji Embedding for Visual Sentiment Analysis
Ziad Al-Halah, Andrew Aitken, Wenzhe Shi +1
Due to the lack of large-scale datasets, the prevailing approach in visual sentiment analysis is to leverage models trained for object classification in large datasets like ImageNe…
Traversing the Continuous Spectrum of Image Retrieval with Deep Dynamic Models
Ziad Al-Halah, Andreas M. Lehrmann, Leonid Sigal
We introduce the first work to tackle the image retrieval problem as a continuous operation. While the proposed approaches in the literature can be roughly categorized into two mai…
Informed Democracy: Voting-based Novelty Detection for Action Recognition
Alina Roitberg, Ziad Al-Halah, Rainer Stiefelhagen
Novelty detection is crucial for real-life applications. While it is common in activity recognition to assume a closed-set setting, i.e. test samples are always of training categor…