In　the　last　two　decades,　object　tracking　has　been　one　of　the　prevalent　fields　in　social　media.　Object　tracking　uses　a　dynamic　model　to　track　the　same　target,　aiming　to　analyze　the　same　social　object　and　its　behavior　in　a　set　of　consecutive　video　frames.　In　this　article,　we　provide　a　comprehensive　survey　on　some　representative　and　latest　correlation-filter-based　object　tracking　methods　and　compare　their　respective　strengths　and　weaknesses　under　the　theoretical　and　experimental　analyses.　First　of　all,　we　divide　these　correlation-filter-based　object　tracking　methods　into　four　categories　according　to　their　characteristics,　including　categorized　features,　space　weight　factors,　scale　factors,　and　expert　strategies.　Second,　extensive　experiments　on　benchmark　datasets　with　11　tracking　challenges　are　performed　and　discussed.　Finally,　this　article　also　attempts　to　provide　some　insights　for　the　readers　to　comprehend　and　improve　the　involved　tracking　algorithms.　It　is　expected　that　the　overview　would　present　a　detailed　framework　and　some　enlightenments　of　object　tracking　to　readers　who　are　new　in　this　area.